From 9b5f75e2f37833250c14e01e91c96fb9e9c80eeb Mon Sep 17 00:00:00 2001 From: Falko Zurell Date: Fri, 16 May 2025 13:27:31 +0200 Subject: [PATCH 01/82] Create traefik-manual-setup.md --- traefik-manual-setup.md | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 traefik-manual-setup.md diff --git a/traefik-manual-setup.md b/traefik-manual-setup.md new file mode 100644 index 0000000..2bb8d33 --- /dev/null +++ b/traefik-manual-setup.md @@ -0,0 +1,37 @@ +# Intro +If you're using Traefik as your reverse proxy in your docker setup, you might want to use it as well to centrally serve the ```/robots.txt``` for all your Traefik fronted services. + +This can be achieved by configuring a single lightweight service to service static files and defining a high priority Traefik HTTP Router rule. + +# Setup +Define a single service to serve the one robots.txt to rule them all. I'm using a lean nginx:alpine docker image in this example: + +``` +services: + robots: + image: nginx:alpine + container_name: robots-server + volumes: + - ./static/:/usr/share/nginx/html/:ro + labels: + - "traefik.enable=true" + # Router for all /robots.txt requests + - "traefik.http.routers.robots.rule=Path(`/robots.txt`)" + - "traefik.http.routers.robots.entrypoints=web,websecure" + - "traefik.http.routers.robots.priority=3000" + - "traefik.http.routers.robots.service=robots" + - "traefik.http.routers.robots.tls.certresolver=letsencrypt" + - "traefik.http.services.robots.loadbalancer.server.port=80" + networks: + - external_network + +networks: + external_network: + name: traefik_external_network + external: true +``` + + +The Traefik HTTP Routers rule explicitly does not contain a Hostname. Traefik will print a warning about this for the TLS setup but it will work. The high priority of 3000 should ensure this rule is evaluated first for incoming requests. + +Place your robots.txt in the local `./static/` directory and NGINX will serve it for all services behind your Traefik proxy. From 684d11d8895788b388323f6c8b1c56f645195605 Mon Sep 17 00:00:00 2001 From: Falko Zurell Date: Fri, 16 May 2025 13:50:58 +0200 Subject: [PATCH 02/82] moved traefik manual setup into docs moved the traefik manual setup into the docs directory and linked to it from the README.md --- README.md | 1 + traefik-manual-setup.md => docs/traefik-manual-setup.md | 0 2 files changed, 1 insertion(+) rename traefik-manual-setup.md => docs/traefik-manual-setup.md (100%) diff --git a/README.md b/README.md index 232b3ed..6183857 100644 --- a/README.md +++ b/README.md @@ -44,6 +44,7 @@ Note that, as stated in the [httpd documentation](https://httpd.apache.org/docs/ middleware plugin for [Traefik](https://traefik.io/traefik/) to automatically add rules of [robots.txt](./robots.txt) file on-the-fly. +- alternatively you can [manually configure Traefik](./docs/traefik-manual-setup.md) to centrally serve a static `robots.txt` ## Contributing A note about contributing: updates should be added/made to `robots.json`. A GitHub action will then generate the updated `robots.txt`, `table-of-bot-metrics.md`, `.htaccess` and `nginx-block-ai-bots.conf`. diff --git a/traefik-manual-setup.md b/docs/traefik-manual-setup.md similarity index 100% rename from traefik-manual-setup.md rename to docs/traefik-manual-setup.md From 8b188d0612414dbee2bfad4ffc2cc1493dae1faa Mon Sep 17 00:00:00 2001 From: Gregory Date: Sat, 26 Jul 2025 23:50:11 -0400 Subject: [PATCH 03/82] Added YaK user-agent to list of robots Added Meltwater's AI to list of bots that use AI and scrape websites. --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index d34e8ec..2599916 100644 --- a/robots.json +++ b/robots.json @@ -587,6 +587,13 @@ "frequency": "Unclear at this time.", "description": "wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support." }, + "YaK": { + "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)", + "respect": "Unclear at this time.", + "function": "By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making." + "frequency": "Unclear at this time.", + "description": "Retrieves data used for Meltwater's AI enabled consumer intelligence suite" + }, "YandexAdditional": { "operator": "[Yandex](https://yandex.ru)", "respect": "[Yes](https://yandex.ru/support/webmaster/en/search-appearance/fast.html?lang=en)", From 9171625db6beb56a6e9bdbb14beb57feca68e69b Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Mon, 28 Jul 2025 08:56:21 -0700 Subject: [PATCH 04/82] fix: remove summaly --- robots.json | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/robots.json b/robots.json index d34e8ec..8e2e48f 100644 --- a/robots.json +++ b/robots.json @@ -531,13 +531,6 @@ "operator": "[Sidetrade](https://www.sidetrade.com)", "respect": "Unclear at this time." }, - "SummalyBot": { - "description": "AI input summarization.", - "frequency": "No information.", - "function": "Extracts data to provide summaries for user; additional usages unclear.", - "operator": "Unclear at this time.", - "respect": "Unclear at this time." - }, "Thinkbot": { "operator": "[Thinkbot](https://www.thinkbot.agency)", "respect": "No", @@ -608,4 +601,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From c15065544a20ee90f010f584763949f049624888 Mon Sep 17 00:00:00 2001 From: Glitz Smarter <100395937+GlitzSmarter@users.noreply.github.com> Date: Mon, 28 Jul 2025 12:54:25 -0400 Subject: [PATCH 05/82] Rewriting function in YaK Rewrote the function to make it clear the quote is according to the page on the Clearwater website. --- robots.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/robots.json b/robots.json index 2599916..4064a2e 100644 --- a/robots.json +++ b/robots.json @@ -590,7 +590,7 @@ "YaK": { "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)", "respect": "Unclear at this time.", - "function": "By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making." + "function": "According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'." "frequency": "Unclear at this time.", "description": "Retrieves data used for Meltwater's AI enabled consumer intelligence suite" }, @@ -615,4 +615,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 12c5368e04a5f8cf605d8259adedbb1f13a45f45 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Mon, 28 Jul 2025 19:29:19 +0100 Subject: [PATCH 06/82] Fix syntax --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 4064a2e..9866185 100644 --- a/robots.json +++ b/robots.json @@ -590,7 +590,7 @@ "YaK": { "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)", "respect": "Unclear at this time.", - "function": "According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'." + "function": "According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'.", "frequency": "Unclear at this time.", "description": "Retrieves data used for Meltwater's AI enabled consumer intelligence suite" }, From 27420d6fedc242feb5e3369f0ff41bc9a77426c5 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Mon, 28 Jul 2025 18:29:57 +0000 Subject: [PATCH 07/82] Merge pull request #164 from GlitzSmarter/main Adding YaK --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 3b3cdb2..75f7864 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 3139d93..83a5db4 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 1182904..69141a6 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -82,6 +82,7 @@ VelenPublicWebCrawler WARDBot Webzio-Extended wpbot +YaK YandexAdditional YandexAdditionalBot YouBot \ No newline at end of file diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 130eba5..3cffc13 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 4483327..d1a8d4b 100644 --- a/robots.txt +++ b/robots.txt @@ -82,6 +82,7 @@ User-agent: VelenPublicWebCrawler User-agent: WARDBot User-agent: Webzio-Extended User-agent: wpbot +User-agent: YaK User-agent: YandexAdditional User-agent: YandexAdditionalBot User-agent: YouBot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 9356be6..21e9c89 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -84,6 +84,7 @@ | WARDBot | WEBSPARK | Unclear at this time. | AI Data Scrapers | Unclear at this time. | WARDBot is an AI data scraper operated by WEBSPARK. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/wardbot | | Webzio\-Extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended | | wpbot | [QuantumCloud](https://www.quantumcloud.com) | Unclear at this time; opt out provided via [Google Form](https://forms.gle/ajBaxygz9jSR8p8G9) | Live chat support and lead generation. | Unclear at this time. | wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support. | +| YaK | [Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence) | Unclear at this time. | According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'. | Unclear at this time. | Retrieves data used for Meltwater's AI enabled consumer intelligence suite | | YandexAdditional | [Yandex](https://yandex.ru) | [Yes](https://yandex.ru/support/webmaster/en/search-appearance/fast.html?lang=en) | Scrapes/analyzes data for the YandexGPT LLM. | No information. | Retrieves data used for YandexGPT quick answers features. | | YandexAdditionalBot | [Yandex](https://yandex.ru) | [Yes](https://yandex.ru/support/webmaster/en/search-appearance/fast.html?lang=en) | Scrapes/analyzes data for the YandexGPT LLM. | No information. | Retrieves data used for YandexGPT quick answers features. | | YouBot | [You](https://about.you.com/youchat/) | [Yes](https://about.you.com/youbot/) | Scrapes data for search engine and LLMs. | No information. | Retrieves data used for You.com web search engine and LLMs. | From 9565c11d4cda0ce46ae0cdef08950c7d6616bfe7 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Mon, 28 Jul 2025 19:19:15 +0000 Subject: [PATCH 08/82] Merge pull request #166 from ai-robots-txt/summaly-bot fix: remove summaly --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 - nginx-block-ai-bots.conf | 2 +- robots.txt | 1 - table-of-bot-metrics.md | 1 - 6 files changed, 3 insertions(+), 6 deletions(-) diff --git a/.htaccess b/.htaccess index 75f7864..a6ea67b 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 83a5db4..22c291c 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 69141a6..4a86b90 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -74,7 +74,6 @@ Scrapy SemrushBot-OCOB SemrushBot-SWA Sidetrade indexer bot -SummalyBot Thinkbot TikTokSpider Timpibot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 3cffc13..009d862 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index d1a8d4b..50ff139 100644 --- a/robots.txt +++ b/robots.txt @@ -74,7 +74,6 @@ User-agent: Scrapy User-agent: SemrushBot-OCOB User-agent: SemrushBot-SWA User-agent: Sidetrade indexer bot -User-agent: SummalyBot User-agent: Thinkbot User-agent: TikTokSpider User-agent: Timpibot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 21e9c89..81eccc5 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -76,7 +76,6 @@ | SemrushBot\-OCOB | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | Data collected is used for the ContentShake AI tool reports. | | SemrushBot\-SWA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Checks URLs on your site for SEO Writing Assistant. | Roughly once every 10 seconds. | Data collected is used for the SEO Writing Assistant tool to check if URL is accessible. | | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. | -| SummalyBot | Unclear at this time. | Unclear at this time. | Extracts data to provide summaries for user; additional usages unclear. | No information. | AI input summarization. | | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | | Timpibot | [Timpi](https://timpi.io) | Unclear at this time. | Scrapes data for use in training LLMs. | No information. | Makes data available for training AI models. | From 085dd1071e800956790957d678e53ad6e64b07a6 Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Tue, 29 Jul 2025 01:11:26 +0000 Subject: [PATCH 09/82] Update from Dark Visitors --- robots.json | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/robots.json b/robots.json index 434805d..1e1b0af 100644 --- a/robots.json +++ b/robots.json @@ -90,6 +90,13 @@ "frequency": "Monthly at present.", "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)." }, + "ChatGPT Agent": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Agents", + "frequency": "Unclear at this time.", + "description": "ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent" + }, "ChatGPT-User": { "operator": "[OpenAI](https://openai.com)", "respect": "Yes", @@ -580,13 +587,13 @@ "frequency": "Unclear at this time.", "description": "wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support." }, - "YaK": { - "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)", - "respect": "Unclear at this time.", - "function": "According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'.", - "frequency": "Unclear at this time.", - "description": "Retrieves data used for Meltwater's AI enabled consumer intelligence suite" - }, + "YaK": { + "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)", + "respect": "Unclear at this time.", + "function": "According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'.", + "frequency": "Unclear at this time.", + "description": "Retrieves data used for Meltwater's AI enabled consumer intelligence suite" + }, "YandexAdditional": { "operator": "[Yandex](https://yandex.ru)", "respect": "[Yes](https://yandex.ru/support/webmaster/en/search-appearance/fast.html?lang=en)", @@ -608,4 +615,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file From 64f9d6ce9cfe97974a30e08cea2a942b704fc0e6 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Wed, 30 Jul 2025 01:05:21 +0000 Subject: [PATCH 10/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index a6ea67b..12f8d05 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 22c291c..4fb1e0d 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 4a86b90..712a625 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -11,6 +11,7 @@ bedrockbot Brightbot 1.0 Bytespider CCBot +ChatGPT Agent ChatGPT-User Claude-SearchBot Claude-User diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 009d862..5ad2969 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 50ff139..32f7efc 100644 --- a/robots.txt +++ b/robots.txt @@ -11,6 +11,7 @@ User-agent: bedrockbot User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot +User-agent: ChatGPT Agent User-agent: ChatGPT-User User-agent: Claude-SearchBot User-agent: Claude-User diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 81eccc5..99b5ba7 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -13,6 +13,7 @@ | Brightbot 1\.0 | Browsing.ai | Unclear at this time. | LLM/AI training. | Unclear at this time. | Scrapes data to train LLMs and AI products focused on website customer support. | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | +| ChatGPT Agent | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | | Claude\-SearchBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | No information provided. | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | | Claude\-User | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | No information provided. | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | From 146a229662b501550cc1162b654de4b68a6e7a4e Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Thu, 31 Jul 2025 01:05:21 +0000 Subject: [PATCH 11/82] Update from Dark Visitors --- robots.json | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/robots.json b/robots.json index 1e1b0af..6e20c66 100644 --- a/robots.json +++ b/robots.json @@ -1,4 +1,11 @@ { + "AddSearchBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Search Crawlers", + "frequency": "Unclear at this time.", + "description": "AddSearchBot is a web crawler that indexes website content for AddSearch's AI-powered site search solution, collecting data to provide fast and accurate search results. More info can be found at https://darkvisitors.com/agents/agents/addsearchbot" + }, "AI2Bot": { "operator": "[Ai2](https://allenai.org/crawler)", "respect": "Yes", @@ -69,6 +76,13 @@ "frequency": "Unclear at this time.", "description": "Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application." }, + "bigsur.ai": { + "operator": "Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai" + }, "Brightbot 1.0": { "operator": "Browsing.ai", "respect": "Unclear at this time.", @@ -132,6 +146,13 @@ "frequency": "No information provided.", "description": "Scrapes data to train LLMs and AI products offered by Anthropic." }, + "CloudVertexBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "CloudVertexBot is a Google-operated crawler available to site owners to request targeted crawls of their own sites for AI training purposes on the Vertex AI platform. More info can be found at https://darkvisitors.com/agents/agents/cloudvertexbot" + }, "cohere-ai": { "operator": "[Cohere](https://cohere.com)", "respect": "Unclear at this time.", @@ -266,11 +287,11 @@ "description": "GoogleAgent-Mariner is an AI agent created by Google that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/googleagent-mariner" }, "GoogleOther": { - "description": "\"Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development.\"", - "frequency": "No information.", - "function": "Scrapes data.", "operator": "Google", - "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)" + "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)", + "function": "Scrapes data.", + "frequency": "No information.", + "description": "\"Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development.\"" }, "GoogleOther-Image": { "description": "\"Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development.\"", @@ -335,6 +356,13 @@ "frequency": "Unclear at this time.", "description": "Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot" }, + "LinerBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot" + }, "meta-externalagent": { "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)", "respect": "Yes", From ff9fc264041ba06d1f4d4f46834ee73e35efc792 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Fri, 1 Aug 2025 01:12:53 +0000 Subject: [PATCH 12/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 4 ++++ nginx-block-ai-bots.conf | 2 +- robots.txt | 4 ++++ table-of-bot-metrics.md | 4 ++++ 6 files changed, 15 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 12f8d05..a8cefe0 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 4fb1e0d..c29c137 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 712a625..c14fa4b 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -1,3 +1,4 @@ +AddSearchBot AI2Bot Ai2Bot-Dolma aiHitBot @@ -8,6 +9,7 @@ Applebot Applebot-Extended Awario bedrockbot +bigsur.ai Brightbot 1.0 Bytespider CCBot @@ -17,6 +19,7 @@ Claude-SearchBot Claude-User Claude-Web ClaudeBot +CloudVertexBot cohere-ai cohere-training-data-crawler Cotoyogi @@ -46,6 +49,7 @@ ImagesiftBot img2dataset ISSCyberRiskCrawler Kangaroo Bot +LinerBot meta-externalagent Meta-ExternalAgent meta-externalfetcher diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 5ad2969..31c5644 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 32f7efc..69d4464 100644 --- a/robots.txt +++ b/robots.txt @@ -1,3 +1,4 @@ +User-agent: AddSearchBot User-agent: AI2Bot User-agent: Ai2Bot-Dolma User-agent: aiHitBot @@ -8,6 +9,7 @@ User-agent: Applebot User-agent: Applebot-Extended User-agent: Awario User-agent: bedrockbot +User-agent: bigsur.ai User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot @@ -17,6 +19,7 @@ User-agent: Claude-SearchBot User-agent: Claude-User User-agent: Claude-Web User-agent: ClaudeBot +User-agent: CloudVertexBot User-agent: cohere-ai User-agent: cohere-training-data-crawler User-agent: Cotoyogi @@ -46,6 +49,7 @@ User-agent: ImagesiftBot User-agent: img2dataset User-agent: ISSCyberRiskCrawler User-agent: Kangaroo Bot +User-agent: LinerBot User-agent: meta-externalagent User-agent: Meta-ExternalAgent User-agent: meta-externalfetcher diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 99b5ba7..458aa3a 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -1,5 +1,6 @@ | Name | Operator | Respects `robots.txt` | Data use | Visit regularity | Description | |------|----------|-----------------------|----------|------------------|-------------| +| AddSearchBot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | AddSearchBot is a web crawler that indexes website content for AddSearch's AI-powered site search solution, collecting data to provide fast and accurate search results. More info can be found at https://darkvisitors.com/agents/agents/addsearchbot | | AI2Bot | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | Ai2Bot\-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | aiHitBot | [aiHit](https://www.aihitdata.com/about) | Yes | A massive, artificial intelligence/machine learning, automated system. | No information provided. | Scrapes data for AI systems. | @@ -10,6 +11,7 @@ | Applebot\-Extended | [Apple](https://support.apple.com/en-us/119829#datausage) | Yes | Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others. | Unclear at this time. | Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools. | | Awario | Awario | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Awario is an AI data scraper operated by Awario. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/awario | | bedrockbot | [Amazon](https://amazon.com) | [Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector) | Data scraping for custom AI applications. | Unclear at this time. | Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application. | +| bigsur\.ai | Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses | Unclear at this time. | AI Assistants | Unclear at this time. | bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai | | Brightbot 1\.0 | Browsing.ai | Unclear at this time. | LLM/AI training. | Unclear at this time. | Scrapes data to train LLMs and AI products focused on website customer support. | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | @@ -19,6 +21,7 @@ | Claude\-User | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | No information provided. | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | | Claude\-Web | Anthropic | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Claude-Web is an AI-related agent operated by Anthropic. It's currently unclear exactly what it's used for, since there's no official documentation. If you can provide more detail, please contact us. More info can be found at https://darkvisitors.com/agents/agents/claude-web | | ClaudeBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | +| CloudVertexBot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | CloudVertexBot is a Google-operated crawler available to site owners to request targeted crawls of their own sites for AI training purposes on the Vertex AI platform. More info can be found at https://darkvisitors.com/agents/agents/cloudvertexbot | | cohere\-ai | [Cohere](https://cohere.com) | Unclear at this time. | Retrieves data to provide responses to user-initiated prompts. | Takes action based on user prompts. | Retrieves data based on user prompts. | | cohere\-training\-data\-crawler | Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products | Unclear at this time. | AI Data Scrapers | Unclear at this time. | cohere-training-data-crawler is a web crawler operated by Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products. More info can be found at https://darkvisitors.com/agents/agents/cohere-training-data-crawler | | Cotoyogi | [ROIS](https://ds.rois.ac.jp/en_center8/en_crawler/) | Yes | AI LLM Scraper. | No information provided. | Scrapes data for AI training in Japanese language. | @@ -48,6 +51,7 @@ | img2dataset | [img2dataset](https://github.com/rom1504/img2dataset) | Unclear at this time. | Scrapes images for use in LLMs. | At the discretion of img2dataset users. | Downloads large sets of images into datasets for LLM training or other purposes. | | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. | | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot | +| LinerBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot | | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | | Meta\-ExternalAgent | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Meta-ExternalAgent is a web crawler used by Meta to download training data for its AI models and improve its products by indexing content directly. More info can be found at https://darkvisitors.com/agents/agents/meta-externalagent | | meta\-externalfetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | From 0e687a5b5875933437e4be7c0daa92353c775ec0 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Wed, 13 Aug 2025 09:01:55 -0700 Subject: [PATCH 13/82] chore: adds OpenAI but user agent --- robots.json | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/robots.json b/robots.json index 6e20c66..6455941 100644 --- a/robots.json +++ b/robots.json @@ -105,8 +105,8 @@ "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)." }, "ChatGPT Agent": { - "operator": "Unclear at this time.", - "respect": "Unclear at this time.", + "operator": "[OpenAI](https://openai.com)", + "respect": "Yes", "function": "AI Agents", "frequency": "Unclear at this time.", "description": "ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent" @@ -447,6 +447,13 @@ "operator": "[Webz.io](https://webz.io/)", "respect": "[Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html)" }, + "OpenAI": { + "operator": "[OpenAI](https://openai.com)", + "respect": "Yes", + "function": "Unclear at this time.", + "frequency": "Unclear at this time.", + "description": "The purpose of this bot is unclear at this time but it is a member of OpenAI's suite of crawlers." + }, "Operator": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -643,4 +650,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 6d3f3e17120b36dba6b959bc646d1deaefa680ea Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Thu, 14 Aug 2025 01:45:05 +0000 Subject: [PATCH 14/82] Merge pull request #167 from ai-robots-txt/OpenAI-bot chore: adds OpenAI but user agent --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 3 ++- 6 files changed, 7 insertions(+), 4 deletions(-) diff --git a/.htaccess b/.htaccess index a8cefe0..46a30f3 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index c29c137..8d82b28 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index c14fa4b..8ccc29f 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -62,6 +62,7 @@ NovaAct OAI-SearchBot omgili omgilibot +OpenAI Operator PanguBot Panscient diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 31c5644..384272c 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 69d4464..498a0b9 100644 --- a/robots.txt +++ b/robots.txt @@ -62,6 +62,7 @@ User-agent: NovaAct User-agent: OAI-SearchBot User-agent: omgili User-agent: omgilibot +User-agent: OpenAI User-agent: Operator User-agent: PanguBot User-agent: Panscient diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 458aa3a..a2301ec 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -15,7 +15,7 @@ | Brightbot 1\.0 | Browsing.ai | Unclear at this time. | LLM/AI training. | Unclear at this time. | Scrapes data to train LLMs and AI products focused on website customer support. | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | -| ChatGPT Agent | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | +| ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | | Claude\-SearchBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | No information provided. | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | | Claude\-User | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | No information provided. | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | @@ -64,6 +64,7 @@ | OAI\-SearchBot | [OpenAI](https://openai.com) | [Yes](https://platform.openai.com/docs/bots) | Search result generation. | No information. | Crawls sites to surface as results in SearchGPT. | | omgili | [Webz.io](https://webz.io/) | [Yes](https://webz.io/blog/web-data/what-is-the-omgili-bot-and-why-is-it-crawling-your-website/) | Data is sold. | No information. | Crawls sites for APIs used by Hootsuite, Sprinklr, NetBase, and other companies. Data also sold for research purposes or LLM training. | | omgilibot | [Webz.io](https://webz.io/) | [Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html) | Data is sold. | No information. | Legacy user agent initially used for Omgili search engine. Unknown if still used, `omgili` agent still used by Webz.io. | +| OpenAI | [OpenAI](https://openai.com) | Yes | Unclear at this time. | Unclear at this time. | The purpose of this bot is unclear at this time but it is a member of OpenAI's suite of crawlers. | | Operator | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | Operator is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/operator | | PanguBot | the Chinese company Huawei | Unclear at this time. | AI Data Scrapers | Unclear at this time. | PanguBot is a web crawler operated by the Chinese company Huawei. It's used to download training data for its multimodal LLM (Large Language Model) called PanGu. More info can be found at https://darkvisitors.com/agents/agents/pangubot | | Panscient | [Panscient](https://panscient.com) | [Yes](https://panscient.com/faq.htm) | Data collection and analysis using machine learning and AI. | The Panscient web crawler will request a page at most once every second from the same domain name or the same IP address. | Compiles data on businesses and business professionals that is structured using AI and machine learning. | From cf073d49f27d8f424553333e9019c5cb0ff718c2 Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Fri, 15 Aug 2025 01:01:42 +0000 Subject: [PATCH 15/82] Update from Dark Visitors --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 6455941..6ae9b9f 100644 --- a/robots.json +++ b/robots.json @@ -650,4 +650,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file From 1a8edfa84af2ffa2de57fc5f8f40133529557fa1 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Tue, 26 Aug 2025 19:39:42 -0700 Subject: [PATCH 16/82] chore: add Google-Firebase and ShapBot --- robots.json | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/robots.json b/robots.json index 6ae9b9f..e1ac3b7 100644 --- a/robots.json +++ b/robots.json @@ -279,8 +279,15 @@ "frequency": "No information.", "description": "Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search." }, + "Google-Firebase": { + "operator": "Google", + "respect": "Unclear at this time.", + "function": "Used as part of AI apps developed by users of Google's Firebase AI products.", + "frequency": "Unclear at this time.", + "description": "Supports Google's Firebase AI products." + }, "GoogleAgent-Mariner": { - "operator": "Unclear at this time.", + "operator": "Google", "respect": "Unclear at this time.", "function": "AI Agents", "frequency": "Unclear at this time.", @@ -566,6 +573,13 @@ "frequency": "Roughly once every 10 seconds.", "description": "Data collected is used for the SEO Writing Assistant tool to check if URL is accessible." }, + "ShapBot": { + "operator": "[Parallel](https://parallel.ai)", + "respect": "[Yes](https://docs.parallel.ai/features/crawler)", + "function": "Collects data for Parallel's web APIs.", + "frequency": "Unclear at this time.", + "description": "ShapBot helps discover and index websites for Parallel's web APIs." + }, "Sidetrade indexer bot": { "description": "AI product training.", "frequency": "No information.", @@ -650,4 +664,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 2ad1c3e8319f44a8044715d878194b64174a2811 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Wed, 27 Aug 2025 10:13:17 +0000 Subject: [PATCH 17/82] Merge pull request #168 from ai-robots-txt/google-firebase-shapbot chore: add Google-Firebase and ShapBot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 2 ++ nginx-block-ai-bots.conf | 2 +- robots.txt | 2 ++ table-of-bot-metrics.md | 4 +++- 6 files changed, 10 insertions(+), 4 deletions(-) diff --git a/.htaccess b/.htaccess index 46a30f3..309b164 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 8d82b28..cc9e7e0 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 8ccc29f..cb9633f 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -38,6 +38,7 @@ FriendlyCrawler Gemini-Deep-Research Google-CloudVertexBot Google-Extended +Google-Firebase GoogleAgent-Mariner GoogleOther GoogleOther-Image @@ -79,6 +80,7 @@ SBIntuitionsBot Scrapy SemrushBot-OCOB SemrushBot-SWA +ShapBot Sidetrade indexer bot Thinkbot TikTokSpider diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 384272c..2115bbe 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 498a0b9..317b84a 100644 --- a/robots.txt +++ b/robots.txt @@ -38,6 +38,7 @@ User-agent: FriendlyCrawler User-agent: Gemini-Deep-Research User-agent: Google-CloudVertexBot User-agent: Google-Extended +User-agent: Google-Firebase User-agent: GoogleAgent-Mariner User-agent: GoogleOther User-agent: GoogleOther-Image @@ -79,6 +80,7 @@ User-agent: SBIntuitionsBot User-agent: Scrapy User-agent: SemrushBot-OCOB User-agent: SemrushBot-SWA +User-agent: ShapBot User-agent: Sidetrade indexer bot User-agent: Thinkbot User-agent: TikTokSpider diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index a2301ec..8966f11 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -40,7 +40,8 @@ | Gemini\-Deep\-Research | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Gemini-Deep-Research is the agent responsible for collecting and scanning resources used in Google Gemini's Deep Research feature, which acts as a personal research assistant. More info can be found at https://darkvisitors.com/agents/agents/gemini-deep-research | | Google\-CloudVertexBot | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Build and manage AI models for businesses employing Vertex AI | No information. | Google-CloudVertexBot crawls sites on the site owners' request when building Vertex AI Agents. | | Google\-Extended | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | LLM training. | No information. | Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search. | -| GoogleAgent\-Mariner | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | GoogleAgent-Mariner is an AI agent created by Google that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/googleagent-mariner | +| Google\-Firebase | Google | Unclear at this time. | Used as part of AI apps developed by users of Google's Firebase AI products. | Unclear at this time. | Supports Google's Firebase AI products. | +| GoogleAgent\-Mariner | Google | Unclear at this time. | AI Agents | Unclear at this time. | GoogleAgent-Mariner is an AI agent created by Google that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/googleagent-mariner | | GoogleOther | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | | GoogleOther\-Image | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | | GoogleOther\-Video | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | @@ -81,6 +82,7 @@ | Scrapy | [Zyte](https://www.zyte.com) | Unclear at this time. | Scrapes data for a variety of uses including training AI. | No information. | "AI and machine learning applications often need large amounts of quality data, and web data extraction is a fast, efficient way to build structured data sets." | | SemrushBot\-OCOB | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | Data collected is used for the ContentShake AI tool reports. | | SemrushBot\-SWA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Checks URLs on your site for SEO Writing Assistant. | Roughly once every 10 seconds. | Data collected is used for the SEO Writing Assistant tool to check if URL is accessible. | +| ShapBot | [Parallel](https://parallel.ai) | [Yes](https://docs.parallel.ai/features/crawler) | Collects data for Parallel's web APIs. | Unclear at this time. | ShapBot helps discover and index websites for Parallel's web APIs. | | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. | | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | From 0ed29412c93c46bb3cf64821833326bf43da964e Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Thu, 28 Aug 2025 00:55:47 +0000 Subject: [PATCH 18/82] Update from Dark Visitors --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index e1ac3b7..25449f4 100644 --- a/robots.json +++ b/robots.json @@ -664,4 +664,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file From ec508ab4349b83f4574bf808021df9aedc12c1c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?L=C3=A1szl=C3=B3=20K=C3=A1rolyi?= Date: Mon, 8 Sep 2025 21:42:06 +0200 Subject: [PATCH 19/82] Update Brightbot operator and details; add meta-webindexer entry - Update Brightbot operator to https://brightdata.com/brightbot. - Change Brightbot frequency to "At least one per minute." - Expand Brightbot description with disguise tactics link. - Add new entry for meta-webindexer under Meta operator. - Set meta-webindexer respect to "Unclear at this time." - Define meta-webindexer function as "AI Assistants." - Set meta-webindexer frequency to "Unhinged, more than 1 per second." - Include meta-webindexer description on improving Meta AI search. --- robots.json | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/robots.json b/robots.json index 25449f4..5faef5a 100644 --- a/robots.json +++ b/robots.json @@ -84,11 +84,11 @@ "description": "bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai" }, "Brightbot 1.0": { - "operator": "Browsing.ai", + "operator": "https://brightdata.com/brightbot", "respect": "Unclear at this time.", "function": "LLM/AI training.", - "frequency": "Unclear at this time.", - "description": "Scrapes data to train LLMs and AI products focused on website customer support." + "frequency": "At least one per minute.", + "description": "Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/)." }, "Bytespider": { "operator": "ByteDance", @@ -391,6 +391,13 @@ "frequency": "Unclear at this time.", "description": "Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher" }, + "meta-webindexer": { + "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/)", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unhinged, more than 1 per second.", + "description": "As per their documentation, \"The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses.\"" + }, "Meta-ExternalFetcher": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -664,4 +671,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 229d1b4dbc63f2780435bc7061c336ecb6fb0763 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Tue, 9 Sep 2025 02:45:32 +0000 Subject: [PATCH 20/82] Merge pull request #174 from karolyi/master Update Brightbot operator and details; add meta-webindexer entry --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 3 ++- 6 files changed, 7 insertions(+), 4 deletions(-) diff --git a/.htaccess b/.htaccess index 309b164..ca00cc0 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|meta\-webindexer|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index cc9e7e0..e2850e4 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|meta\-webindexer|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index cb9633f..7d3224b 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -54,6 +54,7 @@ LinerBot meta-externalagent Meta-ExternalAgent meta-externalfetcher +meta-webindexer Meta-ExternalFetcher MistralAI-User MistralAI-User/1.0 diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 2115bbe..45eeb25 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|meta\-webindexer|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 317b84a..5f1aee6 100644 --- a/robots.txt +++ b/robots.txt @@ -54,6 +54,7 @@ User-agent: LinerBot User-agent: meta-externalagent User-agent: Meta-ExternalAgent User-agent: meta-externalfetcher +User-agent: meta-webindexer User-agent: Meta-ExternalFetcher User-agent: MistralAI-User User-agent: MistralAI-User/1.0 diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 8966f11..9fc01c2 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -12,7 +12,7 @@ | Awario | Awario | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Awario is an AI data scraper operated by Awario. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/awario | | bedrockbot | [Amazon](https://amazon.com) | [Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector) | Data scraping for custom AI applications. | Unclear at this time. | Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application. | | bigsur\.ai | Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses | Unclear at this time. | AI Assistants | Unclear at this time. | bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai | -| Brightbot 1\.0 | Browsing.ai | Unclear at this time. | LLM/AI training. | Unclear at this time. | Scrapes data to train LLMs and AI products focused on website customer support. | +| Brightbot 1\.0 | https://brightdata.com/brightbot | Unclear at this time. | LLM/AI training. | At least one per minute. | Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/). | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | | ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | @@ -56,6 +56,7 @@ | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | | Meta\-ExternalAgent | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Meta-ExternalAgent is a web crawler used by Meta to download training data for its AI models and improve its products by indexing content directly. More info can be found at https://darkvisitors.com/agents/agents/meta-externalagent | | meta\-externalfetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | +| meta\-webindexer | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/) | Unclear at this time. | AI Assistants | Unhinged, more than 1 per second. | As per their documentation, "The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses." | | Meta\-ExternalFetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | | MistralAI\-User | Mistral | Unclear at this time. | AI Assistants | Unclear at this time. | MistralAI-User is an AI assistant operated by Mistral. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/mistralai-user | | MistralAI\-User/1\.0 | Mistral AI | Yes | Takes action based on user prompts. | Only when prompted by a user. | MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response. | From dd391bf9601cb57c3129c45d1ea7883bd983e146 Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Wed, 10 Sep 2025 00:53:56 +0000 Subject: [PATCH 21/82] Update from Dark Visitors --- robots.json | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/robots.json b/robots.json index 5faef5a..6267d89 100644 --- a/robots.json +++ b/robots.json @@ -391,13 +391,6 @@ "frequency": "Unclear at this time.", "description": "Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher" }, - "meta-webindexer": { - "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/)", - "respect": "Unclear at this time.", - "function": "AI Assistants", - "frequency": "Unhinged, more than 1 per second.", - "description": "As per their documentation, \"The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses.\"" - }, "Meta-ExternalFetcher": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -405,6 +398,13 @@ "frequency": "Unclear at this time.", "description": "Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher" }, + "meta-webindexer": { + "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/)", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unhinged, more than 1 per second.", + "description": "As per their documentation, \"The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses.\"" + }, "MistralAI-User": { "operator": "Mistral", "respect": "Unclear at this time.", @@ -671,4 +671,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file From 50870ba911119111d723ab02741b3f4353e248ff Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Wed, 10 Sep 2025 12:04:08 +0200 Subject: [PATCH 22/82] Add TerraCotta Example server log: X.X.X.X - - [10/Sep/2025:00:06:17 +0000] "GET /archives/dri-devel/2023-November/430875.html HTTP/1.1" 200 7388 "-" "TerraCotta https://github.com/CeramicTeam/CeramicTerracotta" --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index 6267d89..d666cd1 100644 --- a/robots.json +++ b/robots.json @@ -104,6 +104,13 @@ "frequency": "Monthly at present.", "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)." }, + "TerraCotta": { + "operator": "[Ceramic AI](https://ceramic.ai/)", + "respect": "[Yes](https://github.com/CeramicTeam/CeramicTerracotta)", + "function": "AI Agents", + "frequency": "Unclear at this time.", + "description": "Downloads data to train LLMs." + }, "ChatGPT Agent": { "operator": "[OpenAI](https://openai.com)", "respect": "Yes", From b6338ddc732dcd94488198a67e176f8281aa93ca Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Wed, 10 Sep 2025 14:11:16 +0000 Subject: [PATCH 23/82] Merge pull request #176 from emersion/TerraCotta Add TerraCotta --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 3 ++- nginx-block-ai-bots.conf | 2 +- robots.txt | 3 ++- table-of-bot-metrics.md | 3 ++- 6 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.htaccess b/.htaccess index ca00cc0..e4722c3 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|meta\-webindexer|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|TerraCotta|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index e2850e4..a423e74 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|meta\-webindexer|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|TerraCotta|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 7d3224b..f91e309 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -13,6 +13,7 @@ bigsur.ai Brightbot 1.0 Bytespider CCBot +TerraCotta ChatGPT Agent ChatGPT-User Claude-SearchBot @@ -54,8 +55,8 @@ LinerBot meta-externalagent Meta-ExternalAgent meta-externalfetcher -meta-webindexer Meta-ExternalFetcher +meta-webindexer MistralAI-User MistralAI-User/1.0 MyCentralAIScraperBot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 45eeb25..10e8dac 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|meta\-webindexer|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|TerraCotta|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 5f1aee6..d3cd344 100644 --- a/robots.txt +++ b/robots.txt @@ -13,6 +13,7 @@ User-agent: bigsur.ai User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot +User-agent: TerraCotta User-agent: ChatGPT Agent User-agent: ChatGPT-User User-agent: Claude-SearchBot @@ -54,8 +55,8 @@ User-agent: LinerBot User-agent: meta-externalagent User-agent: Meta-ExternalAgent User-agent: meta-externalfetcher -User-agent: meta-webindexer User-agent: Meta-ExternalFetcher +User-agent: meta-webindexer User-agent: MistralAI-User User-agent: MistralAI-User/1.0 User-agent: MyCentralAIScraperBot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 9fc01c2..0058ce9 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -15,6 +15,7 @@ | Brightbot 1\.0 | https://brightdata.com/brightbot | Unclear at this time. | LLM/AI training. | At least one per minute. | Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/). | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | +| TerraCotta | [Ceramic AI](https://ceramic.ai/) | [Yes](https://github.com/CeramicTeam/CeramicTerracotta) | AI Agents | Unclear at this time. | Downloads data to train LLMs. | | ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | | Claude\-SearchBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | No information provided. | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | @@ -56,8 +57,8 @@ | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | | Meta\-ExternalAgent | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Meta-ExternalAgent is a web crawler used by Meta to download training data for its AI models and improve its products by indexing content directly. More info can be found at https://darkvisitors.com/agents/agents/meta-externalagent | | meta\-externalfetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | -| meta\-webindexer | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/) | Unclear at this time. | AI Assistants | Unhinged, more than 1 per second. | As per their documentation, "The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses." | | Meta\-ExternalFetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | +| meta\-webindexer | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/) | Unclear at this time. | AI Assistants | Unhinged, more than 1 per second. | As per their documentation, "The Meta-WebIndexer crawler navigates the web to improve Meta AI search result quality for users. In doing so, Meta analyzes online content to enhance the relevance and accuracy of Meta AI. Allowing Meta-WebIndexer in your robots.txt file helps us cite and link to your content in Meta AI's responses." | | MistralAI\-User | Mistral | Unclear at this time. | AI Assistants | Unclear at this time. | MistralAI-User is an AI assistant operated by Mistral. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/mistralai-user | | MistralAI\-User/1\.0 | Mistral AI | Yes | Takes action based on user prompts. | Only when prompted by a user. | MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response. | | MyCentralAIScraperBot | Unclear at this time. | Unclear at this time. | AI data scraper | Unclear at this time. | Operator and data use is unclear at this time. | From 2fd93029ca750ce87969cbd0464a9685d9c37e8c Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Thu, 11 Sep 2025 00:55:06 +0000 Subject: [PATCH 24/82] Update from Dark Visitors --- robots.json | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/robots.json b/robots.json index d666cd1..7f9aaa0 100644 --- a/robots.json +++ b/robots.json @@ -104,13 +104,6 @@ "frequency": "Monthly at present.", "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)." }, - "TerraCotta": { - "operator": "[Ceramic AI](https://ceramic.ai/)", - "respect": "[Yes](https://github.com/CeramicTeam/CeramicTerracotta)", - "function": "AI Agents", - "frequency": "Unclear at this time.", - "description": "Downloads data to train LLMs." - }, "ChatGPT Agent": { "operator": "[OpenAI](https://openai.com)", "respect": "Yes", @@ -601,6 +594,13 @@ "operator": "[Sidetrade](https://www.sidetrade.com)", "respect": "Unclear at this time." }, + "TerraCotta": { + "operator": "[Ceramic AI](https://ceramic.ai/)", + "respect": "[Yes](https://github.com/CeramicTeam/CeramicTerracotta)", + "function": "AI Agents", + "frequency": "Unclear at this time.", + "description": "Downloads data to train LLMs." + }, "Thinkbot": { "operator": "[Thinkbot](https://www.thinkbot.agency)", "respect": "No", From 8906f6b44790a9296c7393d9455274e7555fe2da Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Fri, 12 Sep 2025 00:53:06 +0000 Subject: [PATCH 25/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 2 +- nginx-block-ai-bots.conf | 2 +- robots.txt | 2 +- table-of-bot-metrics.md | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/.htaccess b/.htaccess index e4722c3..0038f88 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|TerraCotta|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index a423e74..5459b40 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|TerraCotta|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index f91e309..d20fedb 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -13,7 +13,6 @@ bigsur.ai Brightbot 1.0 Bytespider CCBot -TerraCotta ChatGPT Agent ChatGPT-User Claude-SearchBot @@ -84,6 +83,7 @@ SemrushBot-OCOB SemrushBot-SWA ShapBot Sidetrade indexer bot +TerraCotta Thinkbot TikTokSpider Timpibot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 10e8dac..17c4ec9 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|TerraCotta|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index d3cd344..6d685b7 100644 --- a/robots.txt +++ b/robots.txt @@ -13,7 +13,6 @@ User-agent: bigsur.ai User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot -User-agent: TerraCotta User-agent: ChatGPT Agent User-agent: ChatGPT-User User-agent: Claude-SearchBot @@ -84,6 +83,7 @@ User-agent: SemrushBot-OCOB User-agent: SemrushBot-SWA User-agent: ShapBot User-agent: Sidetrade indexer bot +User-agent: TerraCotta User-agent: Thinkbot User-agent: TikTokSpider User-agent: Timpibot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 0058ce9..73ec1f2 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -15,7 +15,6 @@ | Brightbot 1\.0 | https://brightdata.com/brightbot | Unclear at this time. | LLM/AI training. | At least one per minute. | Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/). | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | -| TerraCotta | [Ceramic AI](https://ceramic.ai/) | [Yes](https://github.com/CeramicTeam/CeramicTerracotta) | AI Agents | Unclear at this time. | Downloads data to train LLMs. | | ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | | Claude\-SearchBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | No information provided. | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | @@ -86,6 +85,7 @@ | SemrushBot\-SWA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Checks URLs on your site for SEO Writing Assistant. | Roughly once every 10 seconds. | Data collected is used for the SEO Writing Assistant tool to check if URL is accessible. | | ShapBot | [Parallel](https://parallel.ai) | [Yes](https://docs.parallel.ai/features/crawler) | Collects data for Parallel's web APIs. | Unclear at this time. | ShapBot helps discover and index websites for Parallel's web APIs. | | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. | +| TerraCotta | [Ceramic AI](https://ceramic.ai/) | [Yes](https://github.com/CeramicTeam/CeramicTerracotta) | AI Agents | Unclear at this time. | Downloads data to train LLMs. | | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | | Timpibot | [Timpi](https://timpi.io) | Unclear at this time. | Scrapes data for use in training LLMs. | No information. | Makes data available for training AI models. | From c6e7d69dd594ee31e5765cde5200bf5cc5469508 Mon Sep 17 00:00:00 2001 From: nisbet-hubbard <87453615+nisbet-hubbard@users.noreply.github.com> Date: Sun, 14 Sep 2025 19:41:36 +0800 Subject: [PATCH 26/82] Update README.md --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index f427af4..9bddbef 100644 --- a/README.md +++ b/README.md @@ -65,6 +65,13 @@ You can subscribe with [Feedly](https://feedly.com/i/subscription/feed/https://g Alternatively, you can also subscribe to new releases with your GitHub account by clicking the ⬇️ on "Watch" button at the top of this page, clicking "Custom" and selecting "Releases". +## License content with RSL + +It is also possible to license your content to AI companies in `robots.txt` using +the [Really Simple Licensing](https://rslstandard.org) standard, with an option of +collective bargaining. A [plugin](https://github.com/Jameswlepage/rsl-wp) currently +implements RSL as well as payment processing for WordPress sites. + ## Report abusive crawlers If you use [Cloudflare's hard block](https://blog.cloudflare.com/declaring-your-aindependence-block-ai-bots-scrapers-and-crawlers-with-a-single-click) alongside this list, you can report abusive crawlers that don't respect `robots.txt` [here](https://docs.google.com/forms/d/e/1FAIpQLScbUZ2vlNSdcsb8LyTeSF7uLzQI96s0BKGoJ6wQ6ocUFNOKEg/viewform). From bf347bdf9150cd53971f3aaeace1117c8b92f7fd Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Wed, 24 Sep 2025 09:42:01 -0700 Subject: [PATCH 27/82] chore(robots.json): add DeepSeekBot --- robots.json | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 7f9aaa0..cec6a08 100644 --- a/robots.json +++ b/robots.json @@ -188,6 +188,13 @@ "frequency": "Unclear at this time.", "description": "Datenbank Crawler is an AI data scraper operated by Datenbank. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/datenbank-crawler" }, + "DeepSeekBot": { + "operator": "DeepSeek", + "respect": "Unclear at this time.", + "function": "Training language models and improving AI products", + "frequency": "Unclear at this time.", + "description": "DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products." + }, "Devin": { "operator": "Devin AI", "respect": "Unclear at this time.", @@ -678,4 +685,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 38d60b928c029f1441786e2ad434a8d6f7254150 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Thu, 25 Sep 2025 10:17:38 +0000 Subject: [PATCH 28/82] Merge pull request #179 from ai-robots-txt/deepseekbot chore(robots.json): add DeepSeekBot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 0038f88..1a40293 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 5459b40..4bc4375 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index d20fedb..de21e84 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -25,6 +25,7 @@ cohere-training-data-crawler Cotoyogi Crawlspace Datenbank Crawler +DeepSeekBot Devin Diffbot DuckAssistBot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 17c4ec9..cfd812a 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 6d685b7..0ba66bf 100644 --- a/robots.txt +++ b/robots.txt @@ -25,6 +25,7 @@ User-agent: cohere-training-data-crawler User-agent: Cotoyogi User-agent: Crawlspace User-agent: Datenbank Crawler +User-agent: DeepSeekBot User-agent: Devin User-agent: Diffbot User-agent: DuckAssistBot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 73ec1f2..8dc8115 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -27,6 +27,7 @@ | Cotoyogi | [ROIS](https://ds.rois.ac.jp/en_center8/en_crawler/) | Yes | AI LLM Scraper. | No information provided. | Scrapes data for AI training in Japanese language. | | Crawlspace | [Crawlspace](https://crawlspace.dev) | [Yes](https://news.ycombinator.com/item?id=42756654) | Scrapes data | Unclear at this time. | Provides crawling services for any purpose, probably including AI model training. | | Datenbank Crawler | Datenbank | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Datenbank Crawler is an AI data scraper operated by Datenbank. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/datenbank-crawler | +| DeepSeekBot | DeepSeek | Unclear at this time. | Training language models and improving AI products | Unclear at this time. | DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products. | | Devin | Devin AI | Unclear at this time. | AI Assistants | Unclear at this time. | Devin is an AI assistant operated by Devin AI. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/devin | | Diffbot | [Diffbot](https://www.diffbot.com/) | At the discretion of Diffbot users. | Aggregates structured web data for monitoring and AI model training. | Unclear at this time. | Diffbot is an application used to parse web pages into structured data; this data is used for monitoring or AI model training. | | DuckAssistBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | DuckAssistBot is used by DuckDuckGo's DuckAssist feature to fetch content and generate realtime AI answers to user searches. More info can be found at https://darkvisitors.com/agents/agents/duckassistbot | From 56d03d46fb1c20f048b194a01d14a4451fe67b6d Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Fri, 26 Sep 2025 00:54:30 +0000 Subject: [PATCH 29/82] Update from Dark Visitors --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index cec6a08..9b32d6d 100644 --- a/robots.json +++ b/robots.json @@ -685,4 +685,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file From 91bf905fa9cc37b3a5a46a1d9c7dccb96241410a Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Wed, 15 Oct 2025 00:56:30 +0000 Subject: [PATCH 30/82] Update from Dark Visitors --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index 9b32d6d..30cd095 100644 --- a/robots.json +++ b/robots.json @@ -293,6 +293,13 @@ "frequency": "Unclear at this time.", "description": "Supports Google's Firebase AI products." }, + "Google-NotebookLM": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "Google-NotebookLM is an AI-powered research and note-taking assistant that helps users synthesize information from their own uploaded sources, such as documents, transcripts, or web content. It can generate summaries, answer questions, and highlight key themes from the materials you provide, acting like a personalized research companion built on Google's Gemini model. Google-NotebookLM fetches source URLs when users add them to their notebooks, enabling the AI to access and analyze those pages for context and insights. More info can be found at https://darkvisitors.com/agents/agents/google-notebooklm" + }, "GoogleAgent-Mariner": { "operator": "Google", "respect": "Unclear at this time.", From 260f5029fec84d60ae844a35d2096eea61105dd4 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Thu, 16 Oct 2025 00:56:33 +0000 Subject: [PATCH 31/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 1a40293..c9fefbc 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 4bc4375..d5549a1 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index de21e84..3c4c373 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -40,6 +40,7 @@ Gemini-Deep-Research Google-CloudVertexBot Google-Extended Google-Firebase +Google-NotebookLM GoogleAgent-Mariner GoogleOther GoogleOther-Image diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index cfd812a..971e340 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 0ba66bf..3526084 100644 --- a/robots.txt +++ b/robots.txt @@ -40,6 +40,7 @@ User-agent: Gemini-Deep-Research User-agent: Google-CloudVertexBot User-agent: Google-Extended User-agent: Google-Firebase +User-agent: Google-NotebookLM User-agent: GoogleAgent-Mariner User-agent: GoogleOther User-agent: GoogleOther-Image diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 8dc8115..dfc986d 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -42,6 +42,7 @@ | Google\-CloudVertexBot | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Build and manage AI models for businesses employing Vertex AI | No information. | Google-CloudVertexBot crawls sites on the site owners' request when building Vertex AI Agents. | | Google\-Extended | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | LLM training. | No information. | Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search. | | Google\-Firebase | Google | Unclear at this time. | Used as part of AI apps developed by users of Google's Firebase AI products. | Unclear at this time. | Supports Google's Firebase AI products. | +| Google\-NotebookLM | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Google-NotebookLM is an AI-powered research and note-taking assistant that helps users synthesize information from their own uploaded sources, such as documents, transcripts, or web content. It can generate summaries, answer questions, and highlight key themes from the materials you provide, acting like a personalized research companion built on Google's Gemini model. Google-NotebookLM fetches source URLs when users add them to their notebooks, enabling the AI to access and analyze those pages for context and insights. More info can be found at https://darkvisitors.com/agents/agents/google-notebooklm | | GoogleAgent\-Mariner | Google | Unclear at this time. | AI Agents | Unclear at this time. | GoogleAgent-Mariner is an AI agent created by Google that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/googleagent-mariner | | GoogleOther | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | | GoogleOther\-Image | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | From 28d2d09633eb17b8512917a9dc7010eef1c17350 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Sun, 19 Oct 2025 14:26:05 -0700 Subject: [PATCH 32/82] chore: add amazon-kendra-, Anomura, Cloudflare-AutoRAG and Bravebot --- robots.json | 34 +++++++++++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) diff --git a/robots.json b/robots.json index 7f9aaa0..e56a5af 100644 --- a/robots.json +++ b/robots.json @@ -34,6 +34,13 @@ "frequency": "No information provided.", "description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses." }, + "amazon-kendra-": { + "operator": "Amazon", + "respect": "Yes", + "function": "Collects data for AI natural language search", + "frequency": "No information provided.", + "description": "Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security." + }, "Andibot": { "operator": "[Andi](https://andisearch.com/)", "respect": "Unclear at this time", @@ -41,6 +48,13 @@ "frequency": "No information provided.", "description": "Scrapes website and provides AI summary." }, + "Anomura": { + "operator": "[Direqt](https://direqt.ai)", + "respect": "Yes", + "function": "Collects data for AI search", + "frequency": "No information provided.", + "description": "Anomura is Direqt's search crawler, it discovers and indexes pages their customers websites." + }, "anthropic-ai": { "operator": "[Anthropic](https://www.anthropic.com)", "respect": "Unclear at this time.", @@ -83,6 +97,13 @@ "frequency": "Unclear at this time.", "description": "bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai" }, + "Bravebot": { + "operator": "https://safe.search.brave.com/help/brave-search-crawler", + "respect": "Yes", + "function": "Collects data for AI search", + "frequency": "Unclear at this time.", + "description": "Brave search has a crawler to discover new pages and index their content." + }, "Brightbot 1.0": { "operator": "https://brightdata.com/brightbot", "respect": "Unclear at this time.", @@ -146,6 +167,13 @@ "frequency": "No information provided.", "description": "Scrapes data to train LLMs and AI products offered by Anthropic." }, + "Cloudflare-AutoRAG": { + "operator": "[Cloudflare](https://developers.cloudflare.com/autorag)", + "respect": "Yes", + "function": "Collects data for AI search", + "frequency": "Unclear at this time.", + "description": "AutoRAG is an all-in-one AI search solution." + }, "CloudVertexBot": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -190,10 +218,10 @@ }, "Devin": { "operator": "Devin AI", - "respect": "Unclear at this time.", + "respect": "Yes", "function": "AI Assistants", "frequency": "Unclear at this time.", - "description": "Devin is an AI assistant operated by Devin AI. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/devin" + "description": "Devin is a collaborative AI teammate built to help ambitious engineering teams achieve more." }, "Diffbot": { "operator": "[Diffbot](https://www.diffbot.com/)", @@ -678,4 +706,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 2fa0e9119cd8489ae2b140bf6e67aeb22c84b210 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Mon, 20 Oct 2025 14:34:43 +0000 Subject: [PATCH 33/82] Merge pull request #183 from ai-robots-txt/cdransf/bot-additions-cloudflare chore: add amazon-kendra-, Anomura, Cloudflare-AutoRAG and Bravebot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 4 ++++ nginx-block-ai-bots.conf | 2 +- robots.txt | 4 ++++ table-of-bot-metrics.md | 6 +++++- 6 files changed, 16 insertions(+), 4 deletions(-) diff --git a/.htaccess b/.htaccess index c9fefbc..d5c7278 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index d5549a1..85db053 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 3c4c373..8f3a78d 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -3,13 +3,16 @@ AI2Bot Ai2Bot-Dolma aiHitBot Amazonbot +amazon-kendra- Andibot +Anomura anthropic-ai Applebot Applebot-Extended Awario bedrockbot bigsur.ai +Bravebot Brightbot 1.0 Bytespider CCBot @@ -19,6 +22,7 @@ Claude-SearchBot Claude-User Claude-Web ClaudeBot +Cloudflare-AutoRAG CloudVertexBot cohere-ai cohere-training-data-crawler diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 971e340..50ce395 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 3526084..c6244df 100644 --- a/robots.txt +++ b/robots.txt @@ -3,13 +3,16 @@ User-agent: AI2Bot User-agent: Ai2Bot-Dolma User-agent: aiHitBot User-agent: Amazonbot +User-agent: amazon-kendra- User-agent: Andibot +User-agent: Anomura User-agent: anthropic-ai User-agent: Applebot User-agent: Applebot-Extended User-agent: Awario User-agent: bedrockbot User-agent: bigsur.ai +User-agent: Bravebot User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot @@ -19,6 +22,7 @@ User-agent: Claude-SearchBot User-agent: Claude-User User-agent: Claude-Web User-agent: ClaudeBot +User-agent: Cloudflare-AutoRAG User-agent: CloudVertexBot User-agent: cohere-ai User-agent: cohere-training-data-crawler diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index dfc986d..3f411c0 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -5,13 +5,16 @@ | Ai2Bot\-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | aiHitBot | [aiHit](https://www.aihitdata.com/about) | Yes | A massive, artificial intelligence/machine learning, automated system. | No information provided. | Scrapes data for AI systems. | | Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. | +| amazon\-kendra\- | Amazon | Yes | Collects data for AI natural language search | No information provided. | Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security. | | Andibot | [Andi](https://andisearch.com/) | Unclear at this time | Search engine using generative AI, AI Search Assistant | No information provided. | Scrapes website and provides AI summary. | +| Anomura | [Direqt](https://direqt.ai) | Yes | Collects data for AI search | No information provided. | Anomura is Direqt's search crawler, it discovers and indexes pages their customers websites. | | anthropic\-ai | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | | Applebot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Applebot is a web crawler used by Apple to index search results that allow the Siri AI Assistant to answer user questions. Siri's answers normally contain references to the website. More info can be found at https://darkvisitors.com/agents/agents/applebot | | Applebot\-Extended | [Apple](https://support.apple.com/en-us/119829#datausage) | Yes | Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others. | Unclear at this time. | Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools. | | Awario | Awario | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Awario is an AI data scraper operated by Awario. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/awario | | bedrockbot | [Amazon](https://amazon.com) | [Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector) | Data scraping for custom AI applications. | Unclear at this time. | Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application. | | bigsur\.ai | Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses | Unclear at this time. | AI Assistants | Unclear at this time. | bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai | +| Bravebot | https://safe.search.brave.com/help/brave-search-crawler | Yes | Collects data for AI search | Unclear at this time. | Brave search has a crawler to discover new pages and index their content. | | Brightbot 1\.0 | https://brightdata.com/brightbot | Unclear at this time. | LLM/AI training. | At least one per minute. | Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/). | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | @@ -21,6 +24,7 @@ | Claude\-User | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | No information provided. | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | | Claude\-Web | Anthropic | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Claude-Web is an AI-related agent operated by Anthropic. It's currently unclear exactly what it's used for, since there's no official documentation. If you can provide more detail, please contact us. More info can be found at https://darkvisitors.com/agents/agents/claude-web | | ClaudeBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | +| Cloudflare\-AutoRAG | [Cloudflare](https://developers.cloudflare.com/autorag) | Yes | Collects data for AI search | Unclear at this time. | AutoRAG is an all-in-one AI search solution. | | CloudVertexBot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | CloudVertexBot is a Google-operated crawler available to site owners to request targeted crawls of their own sites for AI training purposes on the Vertex AI platform. More info can be found at https://darkvisitors.com/agents/agents/cloudvertexbot | | cohere\-ai | [Cohere](https://cohere.com) | Unclear at this time. | Retrieves data to provide responses to user-initiated prompts. | Takes action based on user prompts. | Retrieves data based on user prompts. | | cohere\-training\-data\-crawler | Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products | Unclear at this time. | AI Data Scrapers | Unclear at this time. | cohere-training-data-crawler is a web crawler operated by Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products. More info can be found at https://darkvisitors.com/agents/agents/cohere-training-data-crawler | @@ -28,7 +32,7 @@ | Crawlspace | [Crawlspace](https://crawlspace.dev) | [Yes](https://news.ycombinator.com/item?id=42756654) | Scrapes data | Unclear at this time. | Provides crawling services for any purpose, probably including AI model training. | | Datenbank Crawler | Datenbank | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Datenbank Crawler is an AI data scraper operated by Datenbank. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/datenbank-crawler | | DeepSeekBot | DeepSeek | Unclear at this time. | Training language models and improving AI products | Unclear at this time. | DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products. | -| Devin | Devin AI | Unclear at this time. | AI Assistants | Unclear at this time. | Devin is an AI assistant operated by Devin AI. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/devin | +| Devin | Devin AI | Yes | AI Assistants | Unclear at this time. | Devin is a collaborative AI teammate built to help ambitious engineering teams achieve more. | | Diffbot | [Diffbot](https://www.diffbot.com/) | At the discretion of Diffbot users. | Aggregates structured web data for monitoring and AI model training. | Unclear at this time. | Diffbot is an application used to parse web pages into structured data; this data is used for monitoring or AI model training. | | DuckAssistBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | DuckAssistBot is used by DuckDuckGo's DuckAssist feature to fetch content and generate realtime AI answers to user searches. More info can be found at https://darkvisitors.com/agents/agents/duckassistbot | | Echobot Bot | Echobox | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Echobot Bot is an AI data scraper operated by Echobox. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/echobot-bot | From 19c1d346c3b53f9236b080891732430ec589a893 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Mon, 20 Oct 2025 09:28:31 -0700 Subject: [PATCH 34/82] chore: adds IbouBot --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index e47f2f2..7b0aba4 100644 --- a/robots.json +++ b/robots.json @@ -370,6 +370,13 @@ "operator": "iAsk", "respect": "No" }, + "IbouBot": { + "operator": "Ibou", + "respect": "Yes", + "function": "Search result generation.", + "frequency": "Unclear at this time.", + "description": "Ibou.io operates a crawler service named IbouBot which fuels and updates our graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine." + }, "ICC-Crawler": { "operator": "[NICT](https://nict.go.jp)", "respect": "Yes", From d22b8dfd7b625e432beb678867873d96737b4a50 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Tue, 21 Oct 2025 01:08:42 +0100 Subject: [PATCH 35/82] Description is third party, not first --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 7b0aba4..e258b3f 100644 --- a/robots.json +++ b/robots.json @@ -375,7 +375,7 @@ "respect": "Yes", "function": "Search result generation.", "frequency": "Unclear at this time.", - "description": "Ibou.io operates a crawler service named IbouBot which fuels and updates our graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine." + "description": "Ibou.io operates a crawler service named IbouBot which fuels and updates their graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine." }, "ICC-Crawler": { "operator": "[NICT](https://nict.go.jp)", From 646ab08e1563b2e2649fe5f7503e64ffa0ebdb8b Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Tue, 21 Oct 2025 00:09:24 +0000 Subject: [PATCH 36/82] Merge pull request #185 from ai-robots-txt/cdransf/add-IbouBot chore: adds IbouBot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index d5c7278..b649f39 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 85db053..3d3749e 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 8f3a78d..5d54072 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -51,6 +51,7 @@ GoogleOther-Image GoogleOther-Video GPTBot iaskspider/2.0 +IbouBot ICC-Crawler ImagesiftBot img2dataset diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 50ce395..d87f65e 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index c6244df..7132637 100644 --- a/robots.txt +++ b/robots.txt @@ -51,6 +51,7 @@ User-agent: GoogleOther-Image User-agent: GoogleOther-Video User-agent: GPTBot User-agent: iaskspider/2.0 +User-agent: IbouBot User-agent: ICC-Crawler User-agent: ImagesiftBot User-agent: img2dataset diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 3f411c0..b0bc6be 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -53,6 +53,7 @@ | GoogleOther\-Video | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | | GPTBot | [OpenAI](https://openai.com) | Yes | Scrapes data to train OpenAI's products. | No information. | Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies. | | iaskspider/2\.0 | iAsk | No | Crawls sites to provide answers to user queries. | Unclear at this time. | Used to provide answers to user queries. | +| IbouBot | Ibou | Yes | Search result generation. | Unclear at this time. | Ibou.io operates a crawler service named IbouBot which fuels and updates their graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine. | | ICC\-Crawler | [NICT](https://nict.go.jp) | Yes | Scrapes data to train and support AI technologies. | No information. | Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business. | | ImagesiftBot | [ImageSift](https://imagesift.com) | [Yes](https://imagesift.com/about) | ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support our suite of web intelligence products | No information. | Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Our web intelligence products use this index to enable search and retrieval of similar images. | | img2dataset | [img2dataset](https://github.com/rom1504/img2dataset) | Unclear at this time. | Scrapes images for use in LLMs. | At the discretion of img2dataset users. | Downloads large sets of images into datasets for LLM training or other purposes. | From b89a9eae6a3e13e5fb7ba6519e635c3901b3217d Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Tue, 21 Oct 2025 01:11:32 +0100 Subject: [PATCH 37/82] Use third party in text, rather than first --- robots.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/robots.json b/robots.json index e258b3f..b4ef751 100644 --- a/robots.json +++ b/robots.json @@ -385,9 +385,9 @@ "description": "Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business." }, "ImagesiftBot": { - "description": "Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Our web intelligence products use this index to enable search and retrieval of similar images.", + "description": "Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Their web intelligence products use this index to enable search and retrieval of similar images.", "frequency": "No information.", - "function": "ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support our suite of web intelligence products", + "function": "ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support their suite of web intelligence products", "operator": "[ImageSift](https://imagesift.com)", "respect": "[Yes](https://imagesift.com/about)" }, From 0bc2361be8a765368eefcf7fc3223cd14151781c Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Tue, 21 Oct 2025 15:23:46 +0000 Subject: [PATCH 38/82] Merge pull request #186 from ai-robots-txt/third-party Use third party in text, rather than first --- table-of-bot-metrics.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index b0bc6be..118e103 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -55,7 +55,7 @@ | iaskspider/2\.0 | iAsk | No | Crawls sites to provide answers to user queries. | Unclear at this time. | Used to provide answers to user queries. | | IbouBot | Ibou | Yes | Search result generation. | Unclear at this time. | Ibou.io operates a crawler service named IbouBot which fuels and updates their graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine. | | ICC\-Crawler | [NICT](https://nict.go.jp) | Yes | Scrapes data to train and support AI technologies. | No information. | Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business. | -| ImagesiftBot | [ImageSift](https://imagesift.com) | [Yes](https://imagesift.com/about) | ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support our suite of web intelligence products | No information. | Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Our web intelligence products use this index to enable search and retrieval of similar images. | +| ImagesiftBot | [ImageSift](https://imagesift.com) | [Yes](https://imagesift.com/about) | ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support their suite of web intelligence products | No information. | Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Their web intelligence products use this index to enable search and retrieval of similar images. | | img2dataset | [img2dataset](https://github.com/rom1504/img2dataset) | Unclear at this time. | Scrapes images for use in LLMs. | At the discretion of img2dataset users. | Downloads large sets of images into datasets for LLM training or other purposes. | | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. | | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot | From 97e19445cec0843d4a5d79045dd447dee387192f Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Fri, 24 Oct 2025 00:53:30 +0000 Subject: [PATCH 39/82] Update from Dark Visitors --- robots.json | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/robots.json b/robots.json index b4ef751..1675f79 100644 --- a/robots.json +++ b/robots.json @@ -27,13 +27,6 @@ "frequency": "No information provided.", "description": "Scrapes data for AI systems." }, - "Amazonbot": { - "operator": "Amazon", - "respect": "Yes", - "function": "Service improvement and enabling answers for Alexa users.", - "frequency": "No information provided.", - "description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses." - }, "amazon-kendra-": { "operator": "Amazon", "respect": "Yes", @@ -41,6 +34,13 @@ "frequency": "No information provided.", "description": "Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security." }, + "Amazonbot": { + "operator": "Amazon", + "respect": "Yes", + "function": "Service improvement and enabling answers for Alexa users.", + "frequency": "No information provided.", + "description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses." + }, "Andibot": { "operator": "[Andi](https://andisearch.com/)", "respect": "Unclear at this time", @@ -371,11 +371,11 @@ "respect": "No" }, "IbouBot": { - "operator": "Ibou", - "respect": "Yes", - "function": "Search result generation.", - "frequency": "Unclear at this time.", - "description": "Ibou.io operates a crawler service named IbouBot which fuels and updates their graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine." + "operator": "Ibou", + "respect": "Yes", + "function": "Search result generation.", + "frequency": "Unclear at this time.", + "description": "Ibou.io operates a crawler service named IbouBot which fuels and updates their graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine." }, "ICC-Crawler": { "operator": "[NICT](https://nict.go.jp)", @@ -727,4 +727,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file From 192b0a2eef17562b8b259c67ef3b2aeeb6709671 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Fri, 24 Oct 2025 10:35:04 -0700 Subject: [PATCH 40/82] chore: adds Linguee Bot --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index 1675f79..493a8c6 100644 --- a/robots.json +++ b/robots.json @@ -419,6 +419,13 @@ "frequency": "Unclear at this time.", "description": "LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot" }, + "Linguee Bot": { + "operator": "[Linguee](https://www.linguee.com)", + "respect": "No", + "function": "AI powered translation service", + "frequency": "Unclear at this time.", + "description": "Linguee Bot is a web crawler used by Linguee to gather training data for its AI powered translation service." + }, "meta-externalagent": { "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)", "respect": "Yes", From 5cad0ee38995e858b55e7d20fcd3804852c03803 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Fri, 24 Oct 2025 18:05:01 +0000 Subject: [PATCH 41/82] Merge pull request #187 from ai-robots-txt/cdransf/add-Linguee-Bot chore: adds Linguee Bot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 3 ++- nginx-block-ai-bots.conf | 2 +- robots.txt | 3 ++- table-of-bot-metrics.md | 3 ++- 6 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.htaccess b/.htaccess index b649f39..93dbca2 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 3d3749e..eac8a34 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 5d54072..ef13b14 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -2,8 +2,8 @@ AddSearchBot AI2Bot Ai2Bot-Dolma aiHitBot -Amazonbot amazon-kendra- +Amazonbot Andibot Anomura anthropic-ai @@ -58,6 +58,7 @@ img2dataset ISSCyberRiskCrawler Kangaroo Bot LinerBot +Linguee Bot meta-externalagent Meta-ExternalAgent meta-externalfetcher diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index d87f65e..9022d20 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|amazon\-kendra\-|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 7132637..ecad630 100644 --- a/robots.txt +++ b/robots.txt @@ -2,8 +2,8 @@ User-agent: AddSearchBot User-agent: AI2Bot User-agent: Ai2Bot-Dolma User-agent: aiHitBot -User-agent: Amazonbot User-agent: amazon-kendra- +User-agent: Amazonbot User-agent: Andibot User-agent: Anomura User-agent: anthropic-ai @@ -58,6 +58,7 @@ User-agent: img2dataset User-agent: ISSCyberRiskCrawler User-agent: Kangaroo Bot User-agent: LinerBot +User-agent: Linguee Bot User-agent: meta-externalagent User-agent: Meta-ExternalAgent User-agent: meta-externalfetcher diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 118e103..eb7d632 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -4,8 +4,8 @@ | AI2Bot | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | Ai2Bot\-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | aiHitBot | [aiHit](https://www.aihitdata.com/about) | Yes | A massive, artificial intelligence/machine learning, automated system. | No information provided. | Scrapes data for AI systems. | -| Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. | | amazon\-kendra\- | Amazon | Yes | Collects data for AI natural language search | No information provided. | Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security. | +| Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. | | Andibot | [Andi](https://andisearch.com/) | Unclear at this time | Search engine using generative AI, AI Search Assistant | No information provided. | Scrapes website and provides AI summary. | | Anomura | [Direqt](https://direqt.ai) | Yes | Collects data for AI search | No information provided. | Anomura is Direqt's search crawler, it discovers and indexes pages their customers websites. | | anthropic\-ai | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | @@ -60,6 +60,7 @@ | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. | | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot | | LinerBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot | +| Linguee Bot | [Linguee](https://www.linguee.com) | No | AI powered translation service | Unclear at this time. | Linguee Bot is a web crawler used by Linguee to gather training data for its AI powered translation service. | | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | | Meta\-ExternalAgent | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Meta-ExternalAgent is a web crawler used by Meta to download training data for its AI models and improve its products by indexing content directly. More info can be found at https://darkvisitors.com/agents/agents/meta-externalagent | | meta\-externalfetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | From 808451055c94c9f080d9e008103f9feead5d9944 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Mon, 3 Nov 2025 13:39:07 -0800 Subject: [PATCH 42/82] chore: adds BuddyBot --- robots.json | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 493a8c6..4d1d917 100644 --- a/robots.json +++ b/robots.json @@ -111,6 +111,13 @@ "frequency": "At least one per minute.", "description": "Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/)." }, + "BuddyBot": { + "operator": "[BuddyBotLearning](https://www.buddybotlearning.com)", + "respect": "Unclear at this time.", + "function": "AI Learning Companion", + "frequency": "Unclear at this time.", + "description": "BuddyBot is a voice-controlled AI learning companion targeted at childhooded STEM education." + }, "Bytespider": { "operator": "ByteDance", "respect": "No", @@ -734,4 +741,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From e87eb706e358af973621fa08f9a9b58465c00039 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Tue, 4 Nov 2025 05:16:28 +0000 Subject: [PATCH 43/82] Merge pull request #188 from ai-robots-txt/cdransf/buddybot chore: adds BuddyBot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 93dbca2..9aab15a 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index eac8a34..90d19a8 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index ef13b14..c7f6f29 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -14,6 +14,7 @@ bedrockbot bigsur.ai Bravebot Brightbot 1.0 +BuddyBot Bytespider CCBot ChatGPT Agent diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 9022d20..e467815 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index ecad630..a3fa7a8 100644 --- a/robots.txt +++ b/robots.txt @@ -14,6 +14,7 @@ User-agent: bedrockbot User-agent: bigsur.ai User-agent: Bravebot User-agent: Brightbot 1.0 +User-agent: BuddyBot User-agent: Bytespider User-agent: CCBot User-agent: ChatGPT Agent diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index eb7d632..a8fad63 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -16,6 +16,7 @@ | bigsur\.ai | Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses | Unclear at this time. | AI Assistants | Unclear at this time. | bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai | | Bravebot | https://safe.search.brave.com/help/brave-search-crawler | Yes | Collects data for AI search | Unclear at this time. | Brave search has a crawler to discover new pages and index their content. | | Brightbot 1\.0 | https://brightdata.com/brightbot | Unclear at this time. | LLM/AI training. | At least one per minute. | Scrapes data to train LLMs and AI products focused on website customer support, [uses residential IPs and legit-looking user-agents to disguise itself](https://ksol.io/en/blog/posts/brightbot-not-that-bright/). | +| BuddyBot | [BuddyBotLearning](https://www.buddybotlearning.com) | Unclear at this time. | AI Learning Companion | Unclear at this time. | BuddyBot is a voice-controlled AI learning companion targeted at childhooded STEM education. | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | | ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | From 00bf2b0e130f7e918ff6f267e20291ed2ef7269c Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Wed, 5 Nov 2025 14:02:37 -0800 Subject: [PATCH 44/82] chore(robots.json): add AmazonBuyForMe and atlassian-bot --- robots.json | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 493a8c6..4d4c389 100644 --- a/robots.json +++ b/robots.json @@ -27,6 +27,20 @@ "frequency": "No information provided.", "description": "Scrapes data for AI systems." }, + "AmazonBuyForMe": { + "operator": "[Amazon](https://amazon.com)", + "respect": "Unclear at this time.", + "function": "AI Agents", + "frequency": "No information provided.", + "description": "Buy For Me is an AI agent that helps buy products at the direction of customers." + }, + "atlassian-bot": { + "operator": "[Atlassian](https://www.atlassian.com)", + "respect": "[Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt)", + "function": "AI search, assistants and agents", + "frequency": "No information provided.", + "description": "atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product." + }, "amazon-kendra-": { "operator": "Amazon", "respect": "Yes", @@ -734,4 +748,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 443dd275277bb42c2dc0d243d28d53c87f20e22f Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Wed, 5 Nov 2025 23:50:59 +0000 Subject: [PATCH 45/82] Merge pull request #189 from ai-robots-txt/cdransf/atlassian-amazon-bots chore(robots.json): add AmazonBuyForMe and atlassian-bot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 2 ++ nginx-block-ai-bots.conf | 2 +- robots.txt | 2 ++ table-of-bot-metrics.md | 2 ++ 6 files changed, 9 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 9aab15a..dc5c512 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 90d19a8..749c9c0 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index c7f6f29..0239a78 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -2,6 +2,8 @@ AddSearchBot AI2Bot Ai2Bot-Dolma aiHitBot +AmazonBuyForMe +atlassian-bot amazon-kendra- Amazonbot Andibot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index e467815..3110a73 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index a3fa7a8..151e698 100644 --- a/robots.txt +++ b/robots.txt @@ -2,6 +2,8 @@ User-agent: AddSearchBot User-agent: AI2Bot User-agent: Ai2Bot-Dolma User-agent: aiHitBot +User-agent: AmazonBuyForMe +User-agent: atlassian-bot User-agent: amazon-kendra- User-agent: Amazonbot User-agent: Andibot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index a8fad63..12afc57 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -4,6 +4,8 @@ | AI2Bot | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | Ai2Bot\-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | aiHitBot | [aiHit](https://www.aihitdata.com/about) | Yes | A massive, artificial intelligence/machine learning, automated system. | No information provided. | Scrapes data for AI systems. | +| AmazonBuyForMe | [Amazon](https://amazon.com) | Unclear at this time. | AI Agents | No information provided. | Buy For Me is an AI agent that helps buy products at the direction of customers. | +| atlassian\-bot | [Atlassian](https://www.atlassian.com) | [Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt) | AI search, assistants and agents | No information provided. | atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product. | | amazon\-kendra\- | Amazon | Yes | Collects data for AI natural language search | No information provided. | Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security. | | Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. | | Andibot | [Andi](https://andisearch.com/) | Unclear at this time | Search engine using generative AI, AI Search Assistant | No information provided. | Scrapes website and provides AI summary. | From 28b45ea08d884419513fc6c8bf65df418da8e379 Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Fri, 14 Nov 2025 11:03:03 -0800 Subject: [PATCH 46/82] chore: adds NotebookLM and KlaviyoAIBot agents --- robots.json | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 493a8c6..4d48d21 100644 --- a/robots.json +++ b/robots.json @@ -412,6 +412,13 @@ "frequency": "Unclear at this time.", "description": "Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot" }, + "KlaviyoAIBot": { + "operator": "[Klaviyo](https://www.klaviyo.com)", + "respect": "[Yes](https://help.klaviyo.com/hc/en-us/articles/40496146232219)", + "function": "AI Search Crawlers", + "frequency": "Indexes based on 'change signals' and user configuration.", + "description": "Indexes content to tailor AI experiences, generate content, answers and recommendations." + }, "LinerBot": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -489,6 +496,13 @@ "frequency": "Unclear at this time.", "description": "netEstate Imprint Crawler is an AI data scraper operated by netEstate. If you think this is incorrect or can provide additional detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/netestate-imprint-crawler" }, + "NotebookLM": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "NotebookLM is an AI-powered research and note-taking assistant that helps users synthesize information from their own uploaded sources, such as documents, transcripts, or web content. It can generate summaries, answer questions, and highlight key themes from the materials you provide, acting like a personalized research companion built on Google's Gemini model. NotebookLM fetches source URLs when users add them to their notebooks, enabling the AI to access and analyze those pages for context and insights. More info can be found at https://darkvisitors.com/agents/agents/google-notebooklm" + }, "NovaAct": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -734,4 +748,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From e2726ac160467687f4d56943f36a639c6758ec38 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Fri, 14 Nov 2025 21:01:25 +0000 Subject: [PATCH 47/82] Merge pull request #192 from ai-robots-txt/cdransf/notebooklm-klaviyo chore: adds NotebookLM and KlaviyoAIBot agents --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 2 ++ nginx-block-ai-bots.conf | 2 +- robots.txt | 2 ++ table-of-bot-metrics.md | 2 ++ 6 files changed, 9 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index dc5c512..ec3c776 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 749c9c0..808469d 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 0239a78..4d9ec3c 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -60,6 +60,7 @@ ImagesiftBot img2dataset ISSCyberRiskCrawler Kangaroo Bot +KlaviyoAIBot LinerBot Linguee Bot meta-externalagent @@ -71,6 +72,7 @@ MistralAI-User MistralAI-User/1.0 MyCentralAIScraperBot netEstate Imprint Crawler +NotebookLM NovaAct OAI-SearchBot omgili diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 3110a73..815bebb 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 151e698..444d92b 100644 --- a/robots.txt +++ b/robots.txt @@ -60,6 +60,7 @@ User-agent: ImagesiftBot User-agent: img2dataset User-agent: ISSCyberRiskCrawler User-agent: Kangaroo Bot +User-agent: KlaviyoAIBot User-agent: LinerBot User-agent: Linguee Bot User-agent: meta-externalagent @@ -71,6 +72,7 @@ User-agent: MistralAI-User User-agent: MistralAI-User/1.0 User-agent: MyCentralAIScraperBot User-agent: netEstate Imprint Crawler +User-agent: NotebookLM User-agent: NovaAct User-agent: OAI-SearchBot User-agent: omgili diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 12afc57..03ccf6e 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -62,6 +62,7 @@ | img2dataset | [img2dataset](https://github.com/rom1504/img2dataset) | Unclear at this time. | Scrapes images for use in LLMs. | At the discretion of img2dataset users. | Downloads large sets of images into datasets for LLM training or other purposes. | | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. | | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot | +| KlaviyoAIBot | [Klaviyo](https://www.klaviyo.com) | [Yes](https://help.klaviyo.com/hc/en-us/articles/40496146232219) | AI Search Crawlers | Indexes based on 'change signals' and user configuration. | Indexes content to tailor AI experiences, generate content, answers and recommendations. | | LinerBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot | | Linguee Bot | [Linguee](https://www.linguee.com) | No | AI powered translation service | Unclear at this time. | Linguee Bot is a web crawler used by Linguee to gather training data for its AI powered translation service. | | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | @@ -73,6 +74,7 @@ | MistralAI\-User/1\.0 | Mistral AI | Yes | Takes action based on user prompts. | Only when prompted by a user. | MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response. | | MyCentralAIScraperBot | Unclear at this time. | Unclear at this time. | AI data scraper | Unclear at this time. | Operator and data use is unclear at this time. | | netEstate Imprint Crawler | netEstate | Unclear at this time. | AI Data Scrapers | Unclear at this time. | netEstate Imprint Crawler is an AI data scraper operated by netEstate. If you think this is incorrect or can provide additional detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/netestate-imprint-crawler | +| NotebookLM | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | NotebookLM is an AI-powered research and note-taking assistant that helps users synthesize information from their own uploaded sources, such as documents, transcripts, or web content. It can generate summaries, answer questions, and highlight key themes from the materials you provide, acting like a personalized research companion built on Google's Gemini model. NotebookLM fetches source URLs when users add them to their notebooks, enabling the AI to access and analyze those pages for context and insights. More info can be found at https://darkvisitors.com/agents/agents/google-notebooklm | | NovaAct | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | Nova Act is an AI agent created by Amazon that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/novaact | | OAI\-SearchBot | [OpenAI](https://openai.com) | [Yes](https://platform.openai.com/docs/bots) | Search result generation. | No information. | Crawls sites to surface as results in SearchGPT. | | omgili | [Webz.io](https://webz.io/) | [Yes](https://webz.io/blog/web-data/what-is-the-omgili-bot-and-why-is-it-crawling-your-website/) | Data is sold. | No information. | Crawls sites for APIs used by Hootsuite, Sprinklr, NetBase, and other companies. Data also sold for research purposes or LLM training. | From efb4d260daefb95487f3d681a035e7a1eb6e0a81 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Thu, 20 Nov 2025 10:23:09 +0000 Subject: [PATCH 48/82] delete extraneous hyphen Fixes https://github.com/ai-robots-txt/ai.robots.txt/issues/193 --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 51adbde..640dcc3 100644 --- a/robots.json +++ b/robots.json @@ -41,7 +41,7 @@ "frequency": "No information provided.", "description": "atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product." }, - "amazon-kendra-": { + "amazon-kendra": { "operator": "Amazon", "respect": "Yes", "function": "Collects data for AI natural language search", From be4d74412c13f465c34d3f6eab6e1ff4c74a92fc Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Fri, 21 Nov 2025 16:32:11 +0000 Subject: [PATCH 49/82] Merge pull request #194 from glyn/193-kendra delete extraneous hyphen --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 2 +- nginx-block-ai-bots.conf | 2 +- robots.txt | 2 +- table-of-bot-metrics.md | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/.htaccess b/.htaccess index ec3c776..0d218d2 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 808469d..c82be67 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 4d9ec3c..6d59918 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -4,7 +4,7 @@ Ai2Bot-Dolma aiHitBot AmazonBuyForMe atlassian-bot -amazon-kendra- +amazon-kendra Amazonbot Andibot Anomura diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 815bebb..938f787 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra\-|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 444d92b..15cc051 100644 --- a/robots.txt +++ b/robots.txt @@ -4,7 +4,7 @@ User-agent: Ai2Bot-Dolma User-agent: aiHitBot User-agent: AmazonBuyForMe User-agent: atlassian-bot -User-agent: amazon-kendra- +User-agent: amazon-kendra User-agent: Amazonbot User-agent: Andibot User-agent: Anomura diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 03ccf6e..7ff323f 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -6,7 +6,7 @@ | aiHitBot | [aiHit](https://www.aihitdata.com/about) | Yes | A massive, artificial intelligence/machine learning, automated system. | No information provided. | Scrapes data for AI systems. | | AmazonBuyForMe | [Amazon](https://amazon.com) | Unclear at this time. | AI Agents | No information provided. | Buy For Me is an AI agent that helps buy products at the direction of customers. | | atlassian\-bot | [Atlassian](https://www.atlassian.com) | [Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt) | AI search, assistants and agents | No information provided. | atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product. | -| amazon\-kendra\- | Amazon | Yes | Collects data for AI natural language search | No information provided. | Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security. | +| amazon\-kendra | Amazon | Yes | Collects data for AI natural language search | No information provided. | Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security. | | Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. | | Andibot | [Andi](https://andisearch.com/) | Unclear at this time | Search engine using generative AI, AI Search Assistant | No information provided. | Scrapes website and provides AI summary. | | Anomura | [Direqt](https://direqt.ai) | Yes | Collects data for AI search | No information provided. | Anomura is Direqt's search crawler, it discovers and indexes pages their customers websites. | From 6225e3e98e308d2832e928342b3c44290a1742d9 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Sun, 23 Nov 2025 04:01:43 +0000 Subject: [PATCH 50/82] Document how to ship a new release --- README.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/README.md b/README.md index 9bddbef..00aff96 100644 --- a/README.md +++ b/README.md @@ -53,6 +53,18 @@ You can run the tests by [installing](https://www.python.org/about/gettingstarte code/tests.py ``` +## Releasing + +Admins may ship a new release `v1.n` (where `n` increments the minor version of the current release) as follows: + +* Navigate to the [new release page](https://github.com/ai-robots-txt/ai.robots.txt/releases/new) on GitHub. +* Click `Select tag`, choose `Create new tag`, enter `v1.n` in the pop-up, and click `Create`. +* Enter a suitable release title (e.g. `v1.n: adds user-agent1, user-agent2`). +* Click `Generate release notes`. +* Click `Publish release`. + +A GitHub action will then add the asset `robots.txt` to the release. That's it. + ## Subscribe to updates You can subscribe to list updates via RSS/Atom with the releases feed: From 0b3266b35f621d01d5d9dae5a99219c42a0f3085 Mon Sep 17 00:00:00 2001 From: fiskhandlarn <680264+fiskhandlarn@users.noreply.github.com> Date: Thu, 20 Nov 2025 11:50:37 +0100 Subject: [PATCH 51/82] feat: allow robots access to `/robots.txt` in nginx --- nginx-block-ai-bots.conf | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 938f787..aefb9e2 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,13 @@ +set $block 0; + if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { + set $block 1; +} + +if ($request_uri = '/robots.txt') { + set $block 0; +} + +if ($block) { return 403; } \ No newline at end of file From ef8eda4fe62b35bc80dbc64810e1dbcf83cfc677 Mon Sep 17 00:00:00 2001 From: fiskhandlarn Date: Tue, 25 Nov 2025 16:39:35 +0100 Subject: [PATCH 52/82] chore: normalize quote style --- nginx-block-ai-bots.conf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index aefb9e2..9a7bdc4 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -4,7 +4,7 @@ if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyFo set $block 1; } -if ($request_uri = '/robots.txt') { +if ($request_uri = "/robots.txt") { set $block 0; } From 2679fcad34088ce1f6a38bc054a1242b90a382df Mon Sep 17 00:00:00 2001 From: fiskhandlarn Date: Tue, 25 Nov 2025 16:46:31 +0100 Subject: [PATCH 53/82] feat: update nginx generator --- code/robots.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/code/robots.py b/code/robots.py index 94a915b..26a4aca 100755 --- a/code/robots.py +++ b/code/robots.py @@ -108,10 +108,10 @@ def clean_robot_name(name): # This was specifically spotted in "Perplexity-User" # Looks like a non-breaking hyphen introduced by the HTML rendering software # Reading the source page for Perplexity: https://docs.perplexity.ai/guides/bots - # You can see the bot is listed several times as "Perplexity-User" with a normal hyphen, + # You can see the bot is listed several times as "Perplexity-User" with a normal hyphen, # and it's only the Row-Heading that has the special hyphen - # - # Technically, there's no reason there wouldn't someday be a bot that + # + # Technically, there's no reason there wouldn't someday be a bot that # actually uses a non-breaking hyphen, but that seems unlikely, # so this solution should be fine for now. result = re.sub(r"\u2011", "-", name) @@ -173,9 +173,9 @@ def json_to_htaccess(robot_json): return htaccess def json_to_nginx(robot_json): - # Creates an Nginx config file. This config snippet can be included in + # Creates an Nginx config file. This config snippet can be included in # nginx server{} blocks to block AI bots. - config = f"if ($http_user_agent ~* \"{list_to_pcre(robot_json.keys())}\") {{\n return 403;\n}}" + config = f"set $block 0;\n\nif ($http_user_agent ~* \"{list_to_pcre(robot_json.keys())}\") {{\n set $block 1;\n}}\n\nif ($request_uri = \"/robots.txt\") {{\n set $block 0;\n}}\n\nif ($block) {{\n return 403;\n}}" return config @@ -225,7 +225,7 @@ def conversions(): file_name="./Caddyfile", converter=json_to_caddy, ) - + update_file_if_changed( file_name="./haproxy-block-ai-bots.txt", converter=json_to_haproxy, From a6cf6b204b9581db5b0bb7353ba69dd237caabe8 Mon Sep 17 00:00:00 2001 From: fiskhandlarn Date: Tue, 25 Nov 2025 16:47:04 +0100 Subject: [PATCH 54/82] test: update test nginx conf --- code/test_files/nginx-block-ai-bots.conf | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/code/test_files/nginx-block-ai-bots.conf b/code/test_files/nginx-block-ai-bots.conf index c569b15..d5e3cc6 100644 --- a/code/test_files/nginx-block-ai-bots.conf +++ b/code/test_files/nginx-block-ai-bots.conf @@ -1,3 +1,13 @@ +set $block 0; + if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|Diffbot|FacebookBot|facebookexternalhit|FriendlyCrawler|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|Meta\-ExternalAgent|Meta\-ExternalFetcher|OAI\-SearchBot|omgili|omgilibot|Perplexity\-User|PerplexityBot|PetalBot|Scrapy|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot|crawler\.with\.dots|star\*\*\*crawler|Is\ this\ a\ crawler\?|a\[mazing\]\{42\}\(robot\)|2\^32\$|curl\|sudo\ bash)") { + set $block 1; +} + +if ($request_uri = "/robots.txt") { + set $block 0; +} + +if ($block) { return 403; } \ No newline at end of file From b681c0c0d8cb76c90cefcbfa360499b7c5fc7a6c Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Wed, 26 Nov 2025 11:54:10 +0000 Subject: [PATCH 55/82] Standardise editor options This was motivated by @fiskhandlarn's comment: https://github.com/ai-robots-txt/ai.robots.txt/pull/195#issuecomment-3576331322 --- .editorconfig | 6 ++++++ README.md | 2 ++ 2 files changed, 8 insertions(+) create mode 100644 .editorconfig diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 0000000..589f816 --- /dev/null +++ b/.editorconfig @@ -0,0 +1,6 @@ +root = true + +[*] +end_of_line = lf +insert_final_newline = true +trim_trailing_whitespace = true diff --git a/README.md b/README.md index 00aff96..0753f0c 100644 --- a/README.md +++ b/README.md @@ -53,6 +53,8 @@ You can run the tests by [installing](https://www.python.org/about/gettingstarte code/tests.py ``` +The `.editorconfig` file provides standard editor options for this project. See [EditorConfig](https://editorconfig.org/) for more information. + ## Releasing Admins may ship a new release `v1.n` (where `n` increments the minor version of the current release) as follows: From ab24e41106367e3161c8f264f6b5f3ce8c938f9c Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Wed, 26 Nov 2025 12:02:42 +0000 Subject: [PATCH 56/82] Clarify that DeepSeekBot does not respect robots.txt Fixes https://github.com/ai-robots-txt/ai.robots.txt/issues/198 --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index 640dcc3..9214874 100644 --- a/robots.json +++ b/robots.json @@ -239,7 +239,7 @@ }, "DeepSeekBot": { "operator": "DeepSeek", - "respect": "Unclear at this time.", + "respect": "No", "function": "Training language models and improving AI products", "frequency": "Unclear at this time.", "description": "DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products." From 35588b2ddb9057cab2096ea509a1f016ab392169 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Wed, 26 Nov 2025 12:07:39 +0000 Subject: [PATCH 57/82] Typo. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6183857..b891ce1 100644 --- a/README.md +++ b/README.md @@ -44,7 +44,7 @@ Note that, as stated in the [httpd documentation](https://httpd.apache.org/docs/ middleware plugin for [Traefik](https://traefik.io/traefik/) to automatically add rules of [robots.txt](./robots.txt) file on-the-fly. -- alternatively you can [manually configure Traefik](./docs/traefik-manual-setup.md) to centrally serve a static `robots.txt` +- Alternatively you can [manually configure Traefik](./docs/traefik-manual-setup.md) to centrally serve a static `robots.txt`. ## Contributing A note about contributing: updates should be added/made to `robots.json`. A GitHub action will then generate the updated `robots.txt`, `table-of-bot-metrics.md`, `.htaccess` and `nginx-block-ai-bots.conf`. From 9cc3dbc05f1a905e73f572a80429c536f09b2c17 Mon Sep 17 00:00:00 2001 From: Anshita-18H Date: Thu, 27 Nov 2025 17:06:59 +0530 Subject: [PATCH 58/82] Add requirements.txt with project dependencies --- requirements.txt | 7 +++++++ 1 file changed, 7 insertions(+) create mode 100644 requirements.txt diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..a8bf87f --- /dev/null +++ b/requirements.txt @@ -0,0 +1,7 @@ +beautifulsoup4 + + + +requests +beautifulsoup4 +lxml From 9ca50339270e410cf6d16b1dc416bbb96729609b Mon Sep 17 00:00:00 2001 From: Anshita-18H Date: Thu, 27 Nov 2025 17:44:47 +0530 Subject: [PATCH 59/82] Deduplicate requirements.txt and add installation instructions to README --- requirements.txt | 4 ---- 1 file changed, 4 deletions(-) diff --git a/requirements.txt b/requirements.txt index a8bf87f..b8ee43c 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,3 @@ -beautifulsoup4 - - - requests beautifulsoup4 lxml From 4302fd1acafd8be96dcc274639b3e21970a91b8f Mon Sep 17 00:00:00 2001 From: Anshita-18H Date: Thu, 27 Nov 2025 17:56:47 +0530 Subject: [PATCH 60/82] Improve contributing section and fix formatting in README --- README.md | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 987cd4a..b1350e0 100644 --- a/README.md +++ b/README.md @@ -49,9 +49,17 @@ file on-the-fly. A note about contributing: updates should be added/made to `robots.json`. A GitHub action will then generate the updated `robots.txt`, `table-of-bot-metrics.md`, `.htaccess` and `nginx-block-ai-bots.conf`. -You can run the tests by [installing](https://www.python.org/about/gettingstarted/) Python 3 and issuing: +You can run the tests by [installing Python 3 and issuing: ```console -code/tests.py +python code/tests.py + + +### Installing Dependencies + +Before running the tests, install all required Python packages: +pip install -r requirements.txt + + ``` ## Releasing @@ -97,3 +105,5 @@ But even if you don't use Cloudflare's hard block, their list of [verified bots] - [Blockin' bots on Netlify](https://www.jeremiak.com/blog/block-bots-netlify-edge-functions/) by Jeremia Kimelman - [Blocking AI web crawlers](https://underlap.org/blocking-ai-web-crawlers) by Glyn Normington - [Block AI Bots from Crawling Websites Using Robots.txt](https://originality.ai/ai-bot-blocking) by Jonathan Gillham, Originality.AI + + From 7521c3af50f2755ae46d6718addedc3e7720eb02 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Thu, 27 Nov 2025 12:37:07 +0000 Subject: [PATCH 61/82] Fix link --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b1350e0..5fbf2c6 100644 --- a/README.md +++ b/README.md @@ -49,7 +49,7 @@ file on-the-fly. A note about contributing: updates should be added/made to `robots.json`. A GitHub action will then generate the updated `robots.txt`, `table-of-bot-metrics.md`, `.htaccess` and `nginx-block-ai-bots.conf`. -You can run the tests by [installing Python 3 and issuing: +You can run the tests by [installing](https://www.python.org/about/gettingstarted/) Python 3, installing the depenendcies, and then issuing: ```console python code/tests.py From c3f2fe758e99b6f2c1afb0fad54ca7b0106ed227 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Thu, 27 Nov 2025 12:37:21 +0000 Subject: [PATCH 62/82] Whitespace --- README.md | 1 - 1 file changed, 1 deletion(-) diff --git a/README.md b/README.md index 5fbf2c6..8aa3e3e 100644 --- a/README.md +++ b/README.md @@ -53,7 +53,6 @@ You can run the tests by [installing](https://www.python.org/about/gettingstarte ```console python code/tests.py - ### Installing Dependencies Before running the tests, install all required Python packages: From f46754d280800f78a891e7e0b834458ce54d39dd Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Thu, 27 Nov 2025 12:37:35 +0000 Subject: [PATCH 63/82] Order deps --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index b8ee43c..664e86d 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,3 @@ -requests beautifulsoup4 lxml +requests From b75163e796fcf1beab7865afadaa14950cd56aaa Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Thu, 27 Nov 2025 12:38:12 +0000 Subject: [PATCH 64/82] Ensure Python3 is used --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 8aa3e3e..305aed2 100644 --- a/README.md +++ b/README.md @@ -51,7 +51,7 @@ A note about contributing: updates should be added/made to `robots.json`. A GitH You can run the tests by [installing](https://www.python.org/about/gettingstarted/) Python 3, installing the depenendcies, and then issuing: ```console -python code/tests.py +code/tests.py ### Installing Dependencies From c26c8c0911bb900e43318f44f9d71fbe680dc4e8 Mon Sep 17 00:00:00 2001 From: Glyn Normington Date: Thu, 27 Nov 2025 12:41:37 +0000 Subject: [PATCH 65/82] Tidy README --- README.md | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 305aed2..c54ced4 100644 --- a/README.md +++ b/README.md @@ -49,16 +49,13 @@ file on-the-fly. A note about contributing: updates should be added/made to `robots.json`. A GitHub action will then generate the updated `robots.txt`, `table-of-bot-metrics.md`, `.htaccess` and `nginx-block-ai-bots.conf`. -You can run the tests by [installing](https://www.python.org/about/gettingstarted/) Python 3, installing the depenendcies, and then issuing: +You can run the tests by [installing](https://www.python.org/about/gettingstarted/) Python 3, installing the dependencies: +```console +pip install -r requirements.txt +``` +and then issuing: ```console code/tests.py - -### Installing Dependencies - -Before running the tests, install all required Python packages: -pip install -r requirements.txt - - ``` ## Releasing From 10d5ae2870ecc4e3f54be3c6ff3d7fa6777c314d Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Thu, 27 Nov 2025 14:00:50 +0000 Subject: [PATCH 66/82] Merge pull request #200 from glyn/deepseek Clarify that DeepSeekBot does not respect robots.txt --- table-of-bot-metrics.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 7ff323f..a706b29 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -34,7 +34,7 @@ | Cotoyogi | [ROIS](https://ds.rois.ac.jp/en_center8/en_crawler/) | Yes | AI LLM Scraper. | No information provided. | Scrapes data for AI training in Japanese language. | | Crawlspace | [Crawlspace](https://crawlspace.dev) | [Yes](https://news.ycombinator.com/item?id=42756654) | Scrapes data | Unclear at this time. | Provides crawling services for any purpose, probably including AI model training. | | Datenbank Crawler | Datenbank | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Datenbank Crawler is an AI data scraper operated by Datenbank. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/datenbank-crawler | -| DeepSeekBot | DeepSeek | Unclear at this time. | Training language models and improving AI products | Unclear at this time. | DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products. | +| DeepSeekBot | DeepSeek | No | Training language models and improving AI products | Unclear at this time. | DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products. | | Devin | Devin AI | Yes | AI Assistants | Unclear at this time. | Devin is a collaborative AI teammate built to help ambitious engineering teams achieve more. | | Diffbot | [Diffbot](https://www.diffbot.com/) | At the discretion of Diffbot users. | Aggregates structured web data for monitoring and AI model training. | Unclear at this time. | Diffbot is an application used to parse web pages into structured data; this data is used for monitoring or AI model training. | | DuckAssistBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | DuckAssistBot is used by DuckDuckGo's DuckAssist feature to fetch content and generate realtime AI answers to user searches. More info can be found at https://darkvisitors.com/agents/agents/duckassistbot | From c6ce9329a1ae8e6c62ce498df3ba912204ee5d4d Mon Sep 17 00:00:00 2001 From: fiskhandlarn Date: Fri, 28 Nov 2025 10:46:22 +0100 Subject: [PATCH 67/82] fix: ensure whitespace as defined in `.editorconfig` --- README.md | 8 +++----- docs/traefik-manual-setup.md | 5 ++--- 2 files changed, 5 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 191104b..586e9f7 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ This list contains AI-related crawlers of all types, regardless of purpose. We encourage you to contribute to and implement this list on your own site. See [information about the listed crawlers](./table-of-bot-metrics.md) and the [FAQ](https://github.com/ai-robots-txt/ai.robots.txt/blob/main/FAQ.md). -A number of these crawlers have been sourced from [Dark Visitors](https://darkvisitors.com) and we appreciate the ongoing effort they put in to track these crawlers. +A number of these crawlers have been sourced from [Dark Visitors](https://darkvisitors.com) and we appreciate the ongoing effort they put in to track these crawlers. If you'd like to add information about a crawler to the list, please make a pull request with the bot name added to `robots.txt`, `ai.txt`, and any relevant details in `table-of-bot-metrics.md` to help people understand what's crawling. @@ -86,8 +86,8 @@ Alternatively, you can also subscribe to new releases with your GitHub account b ## License content with RSL -It is also possible to license your content to AI companies in `robots.txt` using -the [Really Simple Licensing](https://rslstandard.org) standard, with an option of +It is also possible to license your content to AI companies in `robots.txt` using +the [Really Simple Licensing](https://rslstandard.org) standard, with an option of collective bargaining. A [plugin](https://github.com/Jameswlepage/rsl-wp) currently implements RSL as well as payment processing for WordPress sites. @@ -103,5 +103,3 @@ But even if you don't use Cloudflare's hard block, their list of [verified bots] - [Blockin' bots on Netlify](https://www.jeremiak.com/blog/block-bots-netlify-edge-functions/) by Jeremia Kimelman - [Blocking AI web crawlers](https://underlap.org/blocking-ai-web-crawlers) by Glyn Normington - [Block AI Bots from Crawling Websites Using Robots.txt](https://originality.ai/ai-bot-blocking) by Jonathan Gillham, Originality.AI - - diff --git a/docs/traefik-manual-setup.md b/docs/traefik-manual-setup.md index 2bb8d33..0760016 100644 --- a/docs/traefik-manual-setup.md +++ b/docs/traefik-manual-setup.md @@ -1,7 +1,7 @@ # Intro If you're using Traefik as your reverse proxy in your docker setup, you might want to use it as well to centrally serve the ```/robots.txt``` for all your Traefik fronted services. -This can be achieved by configuring a single lightweight service to service static files and defining a high priority Traefik HTTP Router rule. +This can be achieved by configuring a single lightweight service to service static files and defining a high priority Traefik HTTP Router rule. # Setup Define a single service to serve the one robots.txt to rule them all. I'm using a lean nginx:alpine docker image in this example: @@ -31,7 +31,6 @@ networks: external: true ``` - -The Traefik HTTP Routers rule explicitly does not contain a Hostname. Traefik will print a warning about this for the TLS setup but it will work. The high priority of 3000 should ensure this rule is evaluated first for incoming requests. +The Traefik HTTP Routers rule explicitly does not contain a Hostname. Traefik will print a warning about this for the TLS setup but it will work. The high priority of 3000 should ensure this rule is evaluated first for incoming requests. Place your robots.txt in the local `./static/` directory and NGINX will serve it for all services behind your Traefik proxy. From 05bbdebeaa19f4aab70656c62808d74196857f88 Mon Sep 17 00:00:00 2001 From: fiskhandlarn Date: Fri, 28 Nov 2025 10:47:22 +0100 Subject: [PATCH 68/82] feat: disallow final newline for files generated by python if any of these files have ending newlines the tests will fail --- .editorconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.editorconfig b/.editorconfig index 589f816..ef3e1a7 100644 --- a/.editorconfig +++ b/.editorconfig @@ -4,3 +4,6 @@ root = true end_of_line = lf insert_final_newline = true trim_trailing_whitespace = true + +[{Caddyfile,haproxy-block-ai-bots.txt,nginx-block-ai-bots.conf}] +insert_final_newline = false From 30d719a09a2a4ae2ab5f23489c80a987c64cdf39 Mon Sep 17 00:00:00 2001 From: Adam Newbold Date: Fri, 28 Nov 2025 14:08:18 -0500 Subject: [PATCH 69/82] Adding LAIONDownloader --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index 9214874..f5d4642 100644 --- a/robots.json +++ b/robots.json @@ -440,6 +440,13 @@ "frequency": "Indexes based on 'change signals' and user configuration.", "description": "Indexes content to tailor AI experiences, generate content, answers and recommendations." }, + "LAIONDownloader": { + "operator": "[Large-scale Artificial Intelligence Open Network](https://laion.ai/)", + "respect": "[No](https://laion.ai/faq/)", + "function": "AI tools and models for machine learning research.", + "frequency": "Unclear at this time.", + "description": "LAIONDownloader is a bot by LAION, a non-profit organization that provides datasets, tools and models to liberate machine learning research." + } "LinerBot": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", From f5d7ccb24382142e7ba9831dad9f0c35dd69ec22 Mon Sep 17 00:00:00 2001 From: Adam Newbold Date: Fri, 28 Nov 2025 14:10:38 -0500 Subject: [PATCH 70/82] Fixed invalid JSON --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index f5d4642..3b0bc85 100644 --- a/robots.json +++ b/robots.json @@ -446,7 +446,7 @@ "function": "AI tools and models for machine learning research.", "frequency": "Unclear at this time.", "description": "LAIONDownloader is a bot by LAION, a non-profit organization that provides datasets, tools and models to liberate machine learning research." - } + }, "LinerBot": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", From 3fadc88a23cf50175b2d761201e1a3bdf364343a Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Sat, 29 Nov 2025 10:00:52 +0000 Subject: [PATCH 71/82] Merge pull request #206 from newbold/main Adding LAIONDownloader --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 0d218d2..d0abb18 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LAIONDownloader|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index c82be67..f78cb3c 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LAIONDownloader|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 6d59918..7876a4d 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -61,6 +61,7 @@ img2dataset ISSCyberRiskCrawler Kangaroo Bot KlaviyoAIBot +LAIONDownloader LinerBot Linguee Bot meta-externalagent diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 9a7bdc4..63b3840 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,6 +1,6 @@ set $block 0; -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LAIONDownloader|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { set $block 1; } diff --git a/robots.txt b/robots.txt index 15cc051..761456c 100644 --- a/robots.txt +++ b/robots.txt @@ -61,6 +61,7 @@ User-agent: img2dataset User-agent: ISSCyberRiskCrawler User-agent: Kangaroo Bot User-agent: KlaviyoAIBot +User-agent: LAIONDownloader User-agent: LinerBot User-agent: Linguee Bot User-agent: meta-externalagent diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index a706b29..1adad8b 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -63,6 +63,7 @@ | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. | | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot | | KlaviyoAIBot | [Klaviyo](https://www.klaviyo.com) | [Yes](https://help.klaviyo.com/hc/en-us/articles/40496146232219) | AI Search Crawlers | Indexes based on 'change signals' and user configuration. | Indexes content to tailor AI experiences, generate content, answers and recommendations. | +| LAIONDownloader | [Large-scale Artificial Intelligence Open Network](https://laion.ai/) | [No](https://laion.ai/faq/) | AI tools and models for machine learning research. | Unclear at this time. | LAIONDownloader is a bot by LAION, a non-profit organization that provides datasets, tools and models to liberate machine learning research. | | LinerBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot | | Linguee Bot | [Linguee](https://www.linguee.com) | No | AI powered translation service | Unclear at this time. | Linguee Bot is a web crawler used by Linguee to gather training data for its AI powered translation service. | | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | From 6d75f3c1c911202824d8b3943a176f98930e7ba5 Mon Sep 17 00:00:00 2001 From: Adam Newbold Date: Mon, 1 Dec 2025 20:18:29 -0500 Subject: [PATCH 72/82] Update robots.py to address error on line 57 Attempting to work around an error that prevents parsing the Dark Visitors site --- code/robots.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/code/robots.py b/code/robots.py index 26a4aca..a2fb7ec 100755 --- a/code/robots.py +++ b/code/robots.py @@ -52,7 +52,16 @@ def updated_robots_json(soup): for agent in section.find_all("a", href=True): name = agent.find("div", {"class": "agent-name"}).get_text().strip() name = clean_robot_name(name) - desc = agent.find("p").get_text().strip() + + # This line below occasionally throws this error: AttributeError: 'NoneType' object has no attribute 'get_text' + #desc = agent.find("p").get_text().strip() + + # Attempting a different way to handle to avoid errors: + p_tag = agent.find("p") + if p_tag is not None: + desc = p_tag.get_text().strip() + else: + desc = "Description unavailable from darkvisitors.com" default_values = { "Unclear at this time.", From 2ccd4435818e761817a6ee10d030789cebcead5b Mon Sep 17 00:00:00 2001 From: Adam Newbold Date: Mon, 1 Dec 2025 20:24:41 -0500 Subject: [PATCH 73/82] Update ai_robots_update.yml with workflow_dispatch Adding workflow_dispatch to enable manual triggers of this schedule job (for testing) --- .github/workflows/ai_robots_update.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/ai_robots_update.yml b/.github/workflows/ai_robots_update.yml index 17c1cc8..e3f0dbf 100644 --- a/.github/workflows/ai_robots_update.yml +++ b/.github/workflows/ai_robots_update.yml @@ -2,6 +2,7 @@ name: Updates for AI robots files on: schedule: - cron: "0 0 * * *" + workflow_dispatch: jobs: dark-visitors: From 8363d4fdd404c03af92115c8b9115952e47749ec Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Tue, 2 Dec 2025 01:25:24 +0000 Subject: [PATCH 74/82] Update from Dark Visitors --- robots.json | 150 +++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 124 insertions(+), 26 deletions(-) diff --git a/robots.json b/robots.json index 3b0bc85..50aadc3 100644 --- a/robots.json +++ b/robots.json @@ -13,12 +13,19 @@ "frequency": "No information provided.", "description": "Explores 'certain domains' to find web content." }, + "AI2Bot-DeepResearchEval": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/ai2bot-deepresearcheval" + }, "Ai2Bot-Dolma": { - "description": "Explores 'certain domains' to find web content.", - "frequency": "No information provided.", - "function": "Content is used to train open language models.", "operator": "[Ai2](https://allenai.org/crawler)", - "respect": "Yes" + "respect": "Yes", + "function": "Content is used to train open language models.", + "frequency": "No information provided.", + "description": "Explores 'certain domains' to find web content." }, "aiHitBot": { "operator": "[aiHit](https://www.aihitdata.com/about)", @@ -27,20 +34,6 @@ "frequency": "No information provided.", "description": "Scrapes data for AI systems." }, - "AmazonBuyForMe": { - "operator": "[Amazon](https://amazon.com)", - "respect": "Unclear at this time.", - "function": "AI Agents", - "frequency": "No information provided.", - "description": "Buy For Me is an AI agent that helps buy products at the direction of customers." - }, - "atlassian-bot": { - "operator": "[Atlassian](https://www.atlassian.com)", - "respect": "[Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt)", - "function": "AI search, assistants and agents", - "frequency": "No information provided.", - "description": "atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product." - }, "amazon-kendra": { "operator": "Amazon", "respect": "Yes", @@ -55,6 +48,13 @@ "frequency": "No information provided.", "description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses." }, + "AmazonBuyForMe": { + "operator": "[Amazon](https://amazon.com)", + "respect": "Unclear at this time.", + "function": "AI Agents", + "frequency": "No information provided.", + "description": "Buy For Me is an AI agent that helps buy products at the direction of customers." + }, "Andibot": { "operator": "[Andi](https://andisearch.com/)", "respect": "Unclear at this time", @@ -90,6 +90,13 @@ "frequency": "Unclear at this time.", "description": "Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools." }, + "atlassian-bot": { + "operator": "[Atlassian](https://www.atlassian.com)", + "respect": "[Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt)", + "function": "AI search, assistants and agents", + "frequency": "No information provided.", + "description": "atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product." + }, "Awario": { "operator": "Awario", "respect": "Unclear at this time.", @@ -146,6 +153,13 @@ "frequency": "Monthly at present.", "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)." }, + "ChatGLM-Spider": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/chatglm-spider" + }, "ChatGPT Agent": { "operator": "[OpenAI](https://openai.com)", "respect": "Yes", @@ -384,6 +398,20 @@ "frequency": "No information.", "description": "Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies." }, + "iAskBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "Undocumented AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/iaskbot" + }, + "iaskspider": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "Undocumented AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/iaskspider" + }, "iaskspider/2.0": { "description": "Used to provide answers to user queries.", "frequency": "Unclear at this time.", @@ -412,6 +440,13 @@ "operator": "[ImageSift](https://imagesift.com)", "respect": "[Yes](https://imagesift.com/about)" }, + "imageSpider": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/imagespider" + }, "img2dataset": { "description": "Downloads large sets of images into datasets for LLM training or other purposes.", "frequency": "At the discretion of img2dataset users.", @@ -440,6 +475,20 @@ "frequency": "Indexes based on 'change signals' and user configuration.", "description": "Indexes content to tailor AI experiences, generate content, answers and recommendations." }, + "KunatoCrawler": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "Undocumented AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/kunatocrawler" + }, + "laion-huggingface-processor": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/laion-huggingface-processor" + }, "LAIONDownloader": { "operator": "[Large-scale Artificial Intelligence Open Network](https://laion.ai/)", "respect": "[No](https://laion.ai/faq/)", @@ -447,6 +496,13 @@ "frequency": "Unclear at this time.", "description": "LAIONDownloader is a bot by LAION, a non-profit organization that provides datasets, tools and models to liberate machine learning research." }, + "LCC": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/lcc" + }, "LinerBot": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -461,6 +517,13 @@ "frequency": "Unclear at this time.", "description": "Linguee Bot is a web crawler used by Linguee to gather training data for its AI powered translation service." }, + "LinkupBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Search Crawlers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/linkupbot" + }, "meta-externalagent": { "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)", "respect": "Yes", @@ -622,6 +685,13 @@ "operator": "[phind](https://www.phind.com/)", "respect": "Unclear at this time." }, + "Poggio-Citations": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/poggio-citations" + }, "Poseidon Research Crawler": { "operator": "[Poseidon Research](https://www.poseidonresearch.com)", "description": "Lab focused on scaling the interpretability research necessary to make better AI systems possible.", @@ -651,11 +721,11 @@ "respect": "Unclear at this time." }, "SBIntuitionsBot": { - "description": "AI development and information analysis", + "operator": "[SB Intuitions](https://www.sbintuitions.co.jp/en/)", "respect": "[Yes](https://www.sbintuitions.co.jp/en/bot/)", - "frequency": "No information.", "function": "Uses data gathered in AI development and information analysis.", - "operator": "[SB Intuitions](https://www.sbintuitions.co.jp/en/)" + "frequency": "No information.", + "description": "AI development and information analysis" }, "Scrapy": { "description": "\"AI and machine learning applications often need large amounts of quality data, and web data extraction is a fast, efficient way to build structured data sets.\"", @@ -692,6 +762,13 @@ "operator": "[Sidetrade](https://www.sidetrade.com)", "respect": "Unclear at this time." }, + "Spider": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/spider" + }, "TerraCotta": { "operator": "[Ceramic AI](https://ceramic.ai/)", "respect": "[Yes](https://github.com/CeramicTeam/CeramicTerracotta)", @@ -721,11 +798,11 @@ "description": "Makes data available for training AI models." }, "VelenPublicWebCrawler": { - "description": "\"Our goal with this crawler is to build business datasets and machine learning models to better understand the web.\"", - "frequency": "No information.", - "function": "Scrapes data for business data sets and machine learning models.", "operator": "[Velen Crawler](https://velen.io)", - "respect": "[Yes](https://velen.io)" + "respect": "[Yes](https://velen.io)", + "function": "Scrapes data for business data sets and machine learning models.", + "frequency": "No information.", + "description": "\"Our goal with this crawler is to build business datasets and machine learning models to better understand the web.\"" }, "WARDBot": { "operator": "WEBSPARK", @@ -741,6 +818,13 @@ "frequency": "Unclear at this time.", "description": "Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended" }, + "webzio-extended": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Data Scrapers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/webzio-extended" + }, "wpbot": { "operator": "[QuantumCloud](https://www.quantumcloud.com)", "respect": "Unclear at this time; opt out provided via [Google Form](https://forms.gle/ajBaxygz9jSR8p8G9)", @@ -748,6 +832,13 @@ "frequency": "Unclear at this time.", "description": "wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support." }, + "WRTNBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "Undocumented AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/wrtnbot" + }, "YaK": { "operator": "[Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence)", "respect": "Unclear at this time.", @@ -775,5 +866,12 @@ "function": "Scrapes data for search engine and LLMs.", "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." + }, + "ZanistaBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Search Crawlers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/zanistabot" } -} +} \ No newline at end of file From f61b3496f7a88e27b48f66e933e09bbafaeec978 Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Wed, 3 Dec 2025 01:00:32 +0000 Subject: [PATCH 75/82] Update from Dark Visitors --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index 50aadc3..ce32e85 100644 --- a/robots.json +++ b/robots.json @@ -524,6 +524,13 @@ "frequency": "Unclear at this time.", "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/linkupbot" }, + "Manus-User": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/manus-user" + }, "meta-externalagent": { "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)", "respect": "Yes", From 45b071b29f38a69400804f6af1c5147f5cfca52a Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Thu, 4 Dec 2025 01:00:27 +0000 Subject: [PATCH 76/82] Update from Dark Visitors --- robots.json | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/robots.json b/robots.json index ce32e85..46ac417 100644 --- a/robots.json +++ b/robots.json @@ -237,6 +237,13 @@ "frequency": "No information provided.", "description": "Scrapes data for AI training in Japanese language." }, + "Crawl4AI": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "Undocumented AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/crawl4ai" + }, "Crawlspace": { "operator": "[Crawlspace](https://crawlspace.dev)", "respect": "[Yes](https://news.ycombinator.com/item?id=42756654)", From 7598d77e4a19fc71f73ba584dfd8858cce0f3827 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Thu, 4 Dec 2025 01:10:02 +0000 Subject: [PATCH 77/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 22 +++++++++++++++++++--- nginx-block-ai-bots.conf | 2 +- robots.txt | 20 ++++++++++++++++++-- table-of-bot-metrics.md | 20 ++++++++++++++++++-- 6 files changed, 58 insertions(+), 10 deletions(-) diff --git a/.htaccess b/.htaccess index d0abb18..3057a25 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LAIONDownloader|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index f78cb3c..28274a5 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LAIONDownloader|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 7876a4d..872c26c 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -1,16 +1,17 @@ AddSearchBot AI2Bot +AI2Bot-DeepResearchEval Ai2Bot-Dolma aiHitBot -AmazonBuyForMe -atlassian-bot amazon-kendra Amazonbot +AmazonBuyForMe Andibot Anomura anthropic-ai Applebot Applebot-Extended +atlassian-bot Awario bedrockbot bigsur.ai @@ -19,6 +20,7 @@ Brightbot 1.0 BuddyBot Bytespider CCBot +ChatGLM-Spider ChatGPT Agent ChatGPT-User Claude-SearchBot @@ -30,6 +32,7 @@ CloudVertexBot cohere-ai cohere-training-data-crawler Cotoyogi +Crawl4AI Crawlspace Datenbank Crawler DeepSeekBot @@ -53,17 +56,25 @@ GoogleOther GoogleOther-Image GoogleOther-Video GPTBot +iAskBot +iaskspider iaskspider/2.0 IbouBot ICC-Crawler ImagesiftBot +imageSpider img2dataset ISSCyberRiskCrawler Kangaroo Bot KlaviyoAIBot +KunatoCrawler +laion-huggingface-processor LAIONDownloader +LCC LinerBot Linguee Bot +LinkupBot +Manus-User meta-externalagent Meta-ExternalAgent meta-externalfetcher @@ -87,6 +98,7 @@ Perplexity-User PerplexityBot PetalBot PhindBot +Poggio-Citations Poseidon Research Crawler QualifiedBot QuillBot @@ -97,6 +109,7 @@ SemrushBot-OCOB SemrushBot-SWA ShapBot Sidetrade indexer bot +Spider TerraCotta Thinkbot TikTokSpider @@ -104,8 +117,11 @@ Timpibot VelenPublicWebCrawler WARDBot Webzio-Extended +webzio-extended wpbot +WRTNBot YaK YandexAdditional YandexAdditionalBot -YouBot \ No newline at end of file +YouBot +ZanistaBot \ No newline at end of file diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 63b3840..e05d924 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,6 +1,6 @@ set $block 0; -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|Ai2Bot\-Dolma|aiHitBot|AmazonBuyForMe|atlassian\-bot|amazon\-kendra|Amazonbot|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|LAIONDownloader|LinerBot|Linguee\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)") { set $block 1; } diff --git a/robots.txt b/robots.txt index 761456c..4f1879d 100644 --- a/robots.txt +++ b/robots.txt @@ -1,16 +1,17 @@ User-agent: AddSearchBot User-agent: AI2Bot +User-agent: AI2Bot-DeepResearchEval User-agent: Ai2Bot-Dolma User-agent: aiHitBot -User-agent: AmazonBuyForMe -User-agent: atlassian-bot User-agent: amazon-kendra User-agent: Amazonbot +User-agent: AmazonBuyForMe User-agent: Andibot User-agent: Anomura User-agent: anthropic-ai User-agent: Applebot User-agent: Applebot-Extended +User-agent: atlassian-bot User-agent: Awario User-agent: bedrockbot User-agent: bigsur.ai @@ -19,6 +20,7 @@ User-agent: Brightbot 1.0 User-agent: BuddyBot User-agent: Bytespider User-agent: CCBot +User-agent: ChatGLM-Spider User-agent: ChatGPT Agent User-agent: ChatGPT-User User-agent: Claude-SearchBot @@ -30,6 +32,7 @@ User-agent: CloudVertexBot User-agent: cohere-ai User-agent: cohere-training-data-crawler User-agent: Cotoyogi +User-agent: Crawl4AI User-agent: Crawlspace User-agent: Datenbank Crawler User-agent: DeepSeekBot @@ -53,17 +56,25 @@ User-agent: GoogleOther User-agent: GoogleOther-Image User-agent: GoogleOther-Video User-agent: GPTBot +User-agent: iAskBot +User-agent: iaskspider User-agent: iaskspider/2.0 User-agent: IbouBot User-agent: ICC-Crawler User-agent: ImagesiftBot +User-agent: imageSpider User-agent: img2dataset User-agent: ISSCyberRiskCrawler User-agent: Kangaroo Bot User-agent: KlaviyoAIBot +User-agent: KunatoCrawler +User-agent: laion-huggingface-processor User-agent: LAIONDownloader +User-agent: LCC User-agent: LinerBot User-agent: Linguee Bot +User-agent: LinkupBot +User-agent: Manus-User User-agent: meta-externalagent User-agent: Meta-ExternalAgent User-agent: meta-externalfetcher @@ -87,6 +98,7 @@ User-agent: Perplexity-User User-agent: PerplexityBot User-agent: PetalBot User-agent: PhindBot +User-agent: Poggio-Citations User-agent: Poseidon Research Crawler User-agent: QualifiedBot User-agent: QuillBot @@ -97,6 +109,7 @@ User-agent: SemrushBot-OCOB User-agent: SemrushBot-SWA User-agent: ShapBot User-agent: Sidetrade indexer bot +User-agent: Spider User-agent: TerraCotta User-agent: Thinkbot User-agent: TikTokSpider @@ -104,9 +117,12 @@ User-agent: Timpibot User-agent: VelenPublicWebCrawler User-agent: WARDBot User-agent: Webzio-Extended +User-agent: webzio-extended User-agent: wpbot +User-agent: WRTNBot User-agent: YaK User-agent: YandexAdditional User-agent: YandexAdditionalBot User-agent: YouBot +User-agent: ZanistaBot Disallow: / diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 1adad8b..6711186 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -2,17 +2,18 @@ |------|----------|-----------------------|----------|------------------|-------------| | AddSearchBot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | AddSearchBot is a web crawler that indexes website content for AddSearch's AI-powered site search solution, collecting data to provide fast and accurate search results. More info can be found at https://darkvisitors.com/agents/agents/addsearchbot | | AI2Bot | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | +| AI2Bot\-DeepResearchEval | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/ai2bot-deepresearcheval | | Ai2Bot\-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. | | aiHitBot | [aiHit](https://www.aihitdata.com/about) | Yes | A massive, artificial intelligence/machine learning, automated system. | No information provided. | Scrapes data for AI systems. | -| AmazonBuyForMe | [Amazon](https://amazon.com) | Unclear at this time. | AI Agents | No information provided. | Buy For Me is an AI agent that helps buy products at the direction of customers. | -| atlassian\-bot | [Atlassian](https://www.atlassian.com) | [Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt) | AI search, assistants and agents | No information provided. | atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product. | | amazon\-kendra | Amazon | Yes | Collects data for AI natural language search | No information provided. | Amazon Kendra is a highly accurate intelligent search service that enables your users to search unstructured data using natural language. It returns specific answers to questions, giving users an experience that's close to interacting with a human expert. It is highly scalable and capable of meeting performance demands, tightly integrated with other AWS services such as Amazon S3 and Amazon Lex, and offers enterprise-grade security. | | Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. | +| AmazonBuyForMe | [Amazon](https://amazon.com) | Unclear at this time. | AI Agents | No information provided. | Buy For Me is an AI agent that helps buy products at the direction of customers. | | Andibot | [Andi](https://andisearch.com/) | Unclear at this time | Search engine using generative AI, AI Search Assistant | No information provided. | Scrapes website and provides AI summary. | | Anomura | [Direqt](https://direqt.ai) | Yes | Collects data for AI search | No information provided. | Anomura is Direqt's search crawler, it discovers and indexes pages their customers websites. | | anthropic\-ai | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | | Applebot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Applebot is a web crawler used by Apple to index search results that allow the Siri AI Assistant to answer user questions. Siri's answers normally contain references to the website. More info can be found at https://darkvisitors.com/agents/agents/applebot | | Applebot\-Extended | [Apple](https://support.apple.com/en-us/119829#datausage) | Yes | Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others. | Unclear at this time. | Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools. | +| atlassian\-bot | [Atlassian](https://www.atlassian.com) | [Yes](https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/#Editing-your-robots.txt) | AI search, assistants and agents | No information provided. | atlassian-bot is a web crawler used to index website content for its AI search, assistants and agents available in its Rovo GenAI product. | | Awario | Awario | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Awario is an AI data scraper operated by Awario. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/awario | | bedrockbot | [Amazon](https://amazon.com) | [Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector) | Data scraping for custom AI applications. | Unclear at this time. | Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application. | | bigsur\.ai | Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses | Unclear at this time. | AI Assistants | Unclear at this time. | bigsur.ai is a web crawler operated by Big Sur AI that fetches website content to enable AI-powered web agents, sales assistants, and content marketing solutions for businesses. More info can be found at https://darkvisitors.com/agents/agents/bigsur-ai | @@ -21,6 +22,7 @@ | BuddyBot | [BuddyBotLearning](https://www.buddybotlearning.com) | Unclear at this time. | AI Learning Companion | Unclear at this time. | BuddyBot is a voice-controlled AI learning companion targeted at childhooded STEM education. | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | +| ChatGLM\-Spider | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/chatglm-spider | | ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | | Claude\-SearchBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | No information provided. | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | @@ -32,6 +34,7 @@ | cohere\-ai | [Cohere](https://cohere.com) | Unclear at this time. | Retrieves data to provide responses to user-initiated prompts. | Takes action based on user prompts. | Retrieves data based on user prompts. | | cohere\-training\-data\-crawler | Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products | Unclear at this time. | AI Data Scrapers | Unclear at this time. | cohere-training-data-crawler is a web crawler operated by Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products. More info can be found at https://darkvisitors.com/agents/agents/cohere-training-data-crawler | | Cotoyogi | [ROIS](https://ds.rois.ac.jp/en_center8/en_crawler/) | Yes | AI LLM Scraper. | No information provided. | Scrapes data for AI training in Japanese language. | +| Crawl4AI | Unclear at this time. | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/crawl4ai | | Crawlspace | [Crawlspace](https://crawlspace.dev) | [Yes](https://news.ycombinator.com/item?id=42756654) | Scrapes data | Unclear at this time. | Provides crawling services for any purpose, probably including AI model training. | | Datenbank Crawler | Datenbank | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Datenbank Crawler is an AI data scraper operated by Datenbank. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/datenbank-crawler | | DeepSeekBot | DeepSeek | No | Training language models and improving AI products | Unclear at this time. | DeepSeekBot is a web crawler used by DeepSeek to train its language models and improve its AI products. | @@ -55,17 +58,25 @@ | GoogleOther\-Image | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | | GoogleOther\-Video | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." | | GPTBot | [OpenAI](https://openai.com) | Yes | Scrapes data to train OpenAI's products. | No information. | Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies. | +| iAskBot | Unclear at this time. | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/iaskbot | +| iaskspider | Unclear at this time. | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/iaskspider | | iaskspider/2\.0 | iAsk | No | Crawls sites to provide answers to user queries. | Unclear at this time. | Used to provide answers to user queries. | | IbouBot | Ibou | Yes | Search result generation. | Unclear at this time. | Ibou.io operates a crawler service named IbouBot which fuels and updates their graph representation of the World Wide Web. This database and all the metrics are used to provide a search engine. | | ICC\-Crawler | [NICT](https://nict.go.jp) | Yes | Scrapes data to train and support AI technologies. | No information. | Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business. | | ImagesiftBot | [ImageSift](https://imagesift.com) | [Yes](https://imagesift.com/about) | ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support their suite of web intelligence products | No information. | Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Their web intelligence products use this index to enable search and retrieval of similar images. | +| imageSpider | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/imagespider | | img2dataset | [img2dataset](https://github.com/rom1504/img2dataset) | Unclear at this time. | Scrapes images for use in LLMs. | At the discretion of img2dataset users. | Downloads large sets of images into datasets for LLM training or other purposes. | | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. | | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot | | KlaviyoAIBot | [Klaviyo](https://www.klaviyo.com) | [Yes](https://help.klaviyo.com/hc/en-us/articles/40496146232219) | AI Search Crawlers | Indexes based on 'change signals' and user configuration. | Indexes content to tailor AI experiences, generate content, answers and recommendations. | +| KunatoCrawler | Unclear at this time. | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/kunatocrawler | +| laion\-huggingface\-processor | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/laion-huggingface-processor | | LAIONDownloader | [Large-scale Artificial Intelligence Open Network](https://laion.ai/) | [No](https://laion.ai/faq/) | AI tools and models for machine learning research. | Unclear at this time. | LAIONDownloader is a bot by LAION, a non-profit organization that provides datasets, tools and models to liberate machine learning research. | +| LCC | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/lcc | | LinerBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | LinerBot is the web crawler used by Liner AI assistant to gather information from academic sources and websites to provide accurate answers with line-by-line source citations for research and scholarly work. More info can be found at https://darkvisitors.com/agents/agents/linerbot | | Linguee Bot | [Linguee](https://www.linguee.com) | No | AI powered translation service | Unclear at this time. | Linguee Bot is a web crawler used by Linguee to gather training data for its AI powered translation service. | +| LinkupBot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/linkupbot | +| Manus\-User | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/manus-user | | meta\-externalagent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." | | Meta\-ExternalAgent | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Meta-ExternalAgent is a web crawler used by Meta to download training data for its AI models and improve its products by indexing content directly. More info can be found at https://darkvisitors.com/agents/agents/meta-externalagent | | meta\-externalfetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher | @@ -89,6 +100,7 @@ | PerplexityBot | [Perplexity](https://www.perplexity.ai/) | [Yes](https://docs.perplexity.ai/guides/bots) | Search result generation. | No information. | Crawls sites to surface as results in Perplexity. | | PetalBot | [Huawei](https://huawei.com/) | Yes | Used to provide recommendations in Hauwei assistant and AI search services. | No explicit frequency provided. | Operated by Huawei to provide search and AI assistant services. | | PhindBot | [phind](https://www.phind.com/) | Unclear at this time. | AI-enhanced search engine. | No explicit frequency provided. | Company offers an AI agent that uses AI and generate extra web query on the fly | +| Poggio\-Citations | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/poggio-citations | | Poseidon Research Crawler | [Poseidon Research](https://www.poseidonresearch.com) | Unclear at this time. | AI research crawler | No explicit frequency provided. | Lab focused on scaling the interpretability research necessary to make better AI systems possible. | | QualifiedBot | [Qualified](https://www.qualified.com) | Unclear at this time. | Company offers AI agents and other related products; usage can be assumed to support said products. | No explicit frequency provided. | Operated by Qualified as part of their suite of AI product offerings. | | QuillBot | [Quillbot](https://quillbot.com) | Unclear at this time. | Company offers AI detection, writing tools and other services. | No explicit frequency provided. | Operated by QuillBot as part of their suite of AI product offerings. | @@ -99,6 +111,7 @@ | SemrushBot\-SWA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Checks URLs on your site for SEO Writing Assistant. | Roughly once every 10 seconds. | Data collected is used for the SEO Writing Assistant tool to check if URL is accessible. | | ShapBot | [Parallel](https://parallel.ai) | [Yes](https://docs.parallel.ai/features/crawler) | Collects data for Parallel's web APIs. | Unclear at this time. | ShapBot helps discover and index websites for Parallel's web APIs. | | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. | +| Spider | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/spider | | TerraCotta | [Ceramic AI](https://ceramic.ai/) | [Yes](https://github.com/CeramicTeam/CeramicTerracotta) | AI Agents | Unclear at this time. | Downloads data to train LLMs. | | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | @@ -106,8 +119,11 @@ | VelenPublicWebCrawler | [Velen Crawler](https://velen.io) | [Yes](https://velen.io) | Scrapes data for business data sets and machine learning models. | No information. | "Our goal with this crawler is to build business datasets and machine learning models to better understand the web." | | WARDBot | WEBSPARK | Unclear at this time. | AI Data Scrapers | Unclear at this time. | WARDBot is an AI data scraper operated by WEBSPARK. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/wardbot | | Webzio\-Extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended | +| webzio\-extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/webzio-extended | | wpbot | [QuantumCloud](https://www.quantumcloud.com) | Unclear at this time; opt out provided via [Google Form](https://forms.gle/ajBaxygz9jSR8p8G9) | Live chat support and lead generation. | Unclear at this time. | wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support. | +| WRTNBot | Unclear at this time. | Unclear at this time. | Undocumented AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/wrtnbot | | YaK | [Meltwater](https://www.meltwater.com/en/suite/consumer-intelligence) | Unclear at this time. | According to the [Meltwater Consumer Intelligence page](https://www.meltwater.com/en/suite/consumer-intelligence) 'By applying AI, data science, and market research expertise to a live feed of global data sources, we transform unstructured data into actionable insights allowing better decision-making'. | Unclear at this time. | Retrieves data used for Meltwater's AI enabled consumer intelligence suite | | YandexAdditional | [Yandex](https://yandex.ru) | [Yes](https://yandex.ru/support/webmaster/en/search-appearance/fast.html?lang=en) | Scrapes/analyzes data for the YandexGPT LLM. | No information. | Retrieves data used for YandexGPT quick answers features. | | YandexAdditionalBot | [Yandex](https://yandex.ru) | [Yes](https://yandex.ru/support/webmaster/en/search-appearance/fast.html?lang=en) | Scrapes/analyzes data for the YandexGPT LLM. | No information. | Retrieves data used for YandexGPT quick answers features. | | YouBot | [You](https://about.you.com/youchat/) | [Yes](https://about.you.com/youbot/) | Scrapes data for search engine and LLMs. | No information. | Retrieves data used for You.com web search engine and LLMs. | +| ZanistaBot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/zanistabot | From 51afa7113a70f912aa944d4c06f9d4a9409d2b81 Mon Sep 17 00:00:00 2001 From: Adam Newbold Date: Wed, 3 Dec 2025 20:15:10 -0500 Subject: [PATCH 78/82] Update ai_robots_update.yml with rebase command to fix scheduled run --- .github/workflows/ai_robots_update.yml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/.github/workflows/ai_robots_update.yml b/.github/workflows/ai_robots_update.yml index e3f0dbf..9622569 100644 --- a/.github/workflows/ai_robots_update.yml +++ b/.github/workflows/ai_robots_update.yml @@ -11,7 +11,7 @@ jobs: steps: - uses: actions/checkout@v4 with: - fetch-depth: 2 + fetch-depth: 0 - run: | pip install beautifulsoup4 requests git config --global user.name "dark-visitors" @@ -23,6 +23,7 @@ jobs: git add -A if ! git diff --cached --quiet; then git commit -m "Update from Dark Visitors" + git rebase origin/main git push else echo "No changes to commit." From f1c752ef12f2370979735369f1d60706ed0a5550 Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Fri, 5 Dec 2025 01:00:44 +0000 Subject: [PATCH 79/82] Update from Dark Visitors --- robots.json | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/robots.json b/robots.json index 46ac417..7c83e50 100644 --- a/robots.json +++ b/robots.json @@ -153,6 +153,13 @@ "frequency": "Monthly at present.", "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers)." }, + "Channel3Bot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Search Crawlers", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/channel3bot" + }, "ChatGLM-Spider": { "operator": "Unclear at this time.", "respect": "Unclear at this time.", @@ -811,6 +818,13 @@ "frequency": "No information.", "description": "Makes data available for training AI models." }, + "TwinAgent": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Agents", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/twinagent" + }, "VelenPublicWebCrawler": { "operator": "[Velen Crawler](https://velen.io)", "respect": "[Yes](https://velen.io)", From 8b8bf9da5d11095dcb5dafe07e757ff5c4439b94 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Sat, 6 Dec 2025 00:58:16 +0000 Subject: [PATCH 80/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 2 ++ nginx-block-ai-bots.conf | 2 +- robots.txt | 2 ++ table-of-bot-metrics.md | 2 ++ 6 files changed, 9 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 3057a25..5d24eb0 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 28274a5..6c71bac 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 872c26c..dc5f083 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -20,6 +20,7 @@ Brightbot 1.0 BuddyBot Bytespider CCBot +Channel3Bot ChatGLM-Spider ChatGPT Agent ChatGPT-User @@ -114,6 +115,7 @@ TerraCotta Thinkbot TikTokSpider Timpibot +TwinAgent VelenPublicWebCrawler WARDBot Webzio-Extended diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index e05d924..abfd15a 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,6 +1,6 @@ set $block 0; -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)") { set $block 1; } diff --git a/robots.txt b/robots.txt index 4f1879d..7e569eb 100644 --- a/robots.txt +++ b/robots.txt @@ -20,6 +20,7 @@ User-agent: Brightbot 1.0 User-agent: BuddyBot User-agent: Bytespider User-agent: CCBot +User-agent: Channel3Bot User-agent: ChatGLM-Spider User-agent: ChatGPT Agent User-agent: ChatGPT-User @@ -114,6 +115,7 @@ User-agent: TerraCotta User-agent: Thinkbot User-agent: TikTokSpider User-agent: Timpibot +User-agent: TwinAgent User-agent: VelenPublicWebCrawler User-agent: WARDBot User-agent: Webzio-Extended diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 6711186..918831c 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -22,6 +22,7 @@ | BuddyBot | [BuddyBotLearning](https://www.buddybotlearning.com) | Unclear at this time. | AI Learning Companion | Unclear at this time. | BuddyBot is a voice-controlled AI learning companion targeted at childhooded STEM education. | | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | +| Channel3Bot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/channel3bot | | ChatGLM\-Spider | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/chatglm-spider | | ChatGPT Agent | [OpenAI](https://openai.com) | Yes | AI Agents | Unclear at this time. | ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/chatgpt-agent | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | @@ -116,6 +117,7 @@ | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | | Timpibot | [Timpi](https://timpi.io) | Unclear at this time. | Scrapes data for use in training LLMs. | No information. | Makes data available for training AI models. | +| TwinAgent | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/twinagent | | VelenPublicWebCrawler | [Velen Crawler](https://velen.io) | [Yes](https://velen.io) | Scrapes data for business data sets and machine learning models. | No information. | "Our goal with this crawler is to build business datasets and machine learning models to better understand the web." | | WARDBot | WEBSPARK | Unclear at this time. | AI Data Scrapers | Unclear at this time. | WARDBot is an AI data scraper operated by WEBSPARK. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/wardbot | | Webzio\-Extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended | From 83485effdb4a31ea010e99cf5dddf14656a998b8 Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Sat, 20 Dec 2025 00:58:49 +0000 Subject: [PATCH 81/82] Update from Dark Visitors --- robots.json | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/robots.json b/robots.json index 7c83e50..e6b283c 100644 --- a/robots.json +++ b/robots.json @@ -700,11 +700,11 @@ "description": "Operated by Huawei to provide search and AI assistant services." }, "PhindBot": { - "description": "Company offers an AI agent that uses AI and generate extra web query on the fly", - "frequency": "No explicit frequency provided.", - "function": "AI-enhanced search engine.", "operator": "[phind](https://www.phind.com/)", - "respect": "Unclear at this time." + "respect": "Unclear at this time.", + "function": "AI-enhanced search engine.", + "frequency": "No explicit frequency provided.", + "description": "Company offers an AI agent that uses AI and generate extra web query on the fly" }, "Poggio-Citations": { "operator": "Unclear at this time.", @@ -790,6 +790,13 @@ "frequency": "Unclear at this time.", "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/spider" }, + "TavilyBot": { + "operator": "Unclear at this time.", + "respect": "Unclear at this time.", + "function": "AI Assistants", + "frequency": "Unclear at this time.", + "description": "Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/tavilybot" + }, "TerraCotta": { "operator": "[Ceramic AI](https://ceramic.ai/)", "respect": "[Yes](https://github.com/CeramicTeam/CeramicTerracotta)", From aa8519ec107d7cfa29b03005c9176708e1269965 Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Sun, 21 Dec 2025 01:07:06 +0000 Subject: [PATCH 82/82] Update from Dark Visitors --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 5d24eb0..20d46d7 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TavilyBot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index 6c71bac..f6e2ec3 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)" + header_regexp User-Agent "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TavilyBot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index dc5f083..3872e58 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -111,6 +111,7 @@ SemrushBot-SWA ShapBot Sidetrade indexer bot Spider +TavilyBot TerraCotta Thinkbot TikTokSpider diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index abfd15a..2288385 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,6 +1,6 @@ set $block 0; -if ($http_user_agent ~* "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)") { +if ($http_user_agent ~* "(AddSearchBot|AI2Bot|AI2Bot\-DeepResearchEval|Ai2Bot\-Dolma|aiHitBot|amazon\-kendra|Amazonbot|AmazonBuyForMe|Andibot|Anomura|anthropic\-ai|Applebot|Applebot\-Extended|atlassian\-bot|Awario|bedrockbot|bigsur\.ai|Bravebot|Brightbot\ 1\.0|BuddyBot|Bytespider|CCBot|Channel3Bot|ChatGLM\-Spider|ChatGPT\ Agent|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|Cloudflare\-AutoRAG|CloudVertexBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawl4AI|Crawlspace|Datenbank\ Crawler|DeepSeekBot|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|Google\-Firebase|Google\-NotebookLM|GoogleAgent\-Mariner|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iAskBot|iaskspider|iaskspider/2\.0|IbouBot|ICC\-Crawler|ImagesiftBot|imageSpider|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|KlaviyoAIBot|KunatoCrawler|laion\-huggingface\-processor|LAIONDownloader|LCC|LinerBot|Linguee\ Bot|LinkupBot|Manus\-User|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|meta\-webindexer|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NotebookLM|NovaAct|OAI\-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poggio\-Citations|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|ShapBot|Sidetrade\ indexer\ bot|Spider|TavilyBot|TerraCotta|Thinkbot|TikTokSpider|Timpibot|TwinAgent|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|webzio\-extended|wpbot|WRTNBot|YaK|YandexAdditional|YandexAdditionalBot|YouBot|ZanistaBot)") { set $block 1; } diff --git a/robots.txt b/robots.txt index 7e569eb..24ce076 100644 --- a/robots.txt +++ b/robots.txt @@ -111,6 +111,7 @@ User-agent: SemrushBot-SWA User-agent: ShapBot User-agent: Sidetrade indexer bot User-agent: Spider +User-agent: TavilyBot User-agent: TerraCotta User-agent: Thinkbot User-agent: TikTokSpider diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 918831c..c43cb99 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -113,6 +113,7 @@ | ShapBot | [Parallel](https://parallel.ai) | [Yes](https://docs.parallel.ai/features/crawler) | Collects data for Parallel's web APIs. | Unclear at this time. | ShapBot helps discover and index websites for Parallel's web APIs. | | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. | | Spider | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/spider | +| TavilyBot | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Description unavailable from darkvisitors.com More info can be found at https://darkvisitors.com/agents/agents/tavilybot | | TerraCotta | [Ceramic AI](https://ceramic.ai/) | [Yes](https://github.com/CeramicTeam/CeramicTerracotta) | AI Agents | Unclear at this time. | Downloads data to train LLMs. | | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. |