Update from Dark Visitors

This commit is contained in:
dark-visitors 2025-06-28 00:58:57 +00:00
commit 7eb2099d3f

View file

@ -55,6 +55,13 @@
"frequency": "Unclear at this time.", "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." "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."
}, },
"Awario": {
"operator": "Awario",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"frequency": "Unclear at this time.",
"description": "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": { "bedrockbot": {
"operator": "[Amazon](https://amazon.com)", "operator": "[Amazon](https://amazon.com)",
"respect": "[Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector)", "respect": "[Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector)",
@ -146,6 +153,20 @@
"frequency": "Unclear at this time.", "frequency": "Unclear at this time.",
"description": "Provides crawling services for any purpose, probably including AI model training." "description": "Provides crawling services for any purpose, probably including AI model training."
}, },
"Datenbank Crawler": {
"operator": "Datenbank",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"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"
},
"Devin": {
"operator": "Devin AI",
"respect": "Unclear at this time.",
"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"
},
"Diffbot": { "Diffbot": {
"operator": "[Diffbot](https://www.diffbot.com/)", "operator": "[Diffbot](https://www.diffbot.com/)",
"respect": "At the discretion of Diffbot users.", "respect": "At the discretion of Diffbot users.",
@ -160,6 +181,13 @@
"frequency": "Unclear at this time.", "frequency": "Unclear at this time.",
"description": "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" "description": "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": {
"operator": "Echobox",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"frequency": "Unclear at this time.",
"description": "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"
},
"EchoboxBot": { "EchoboxBot": {
"operator": "[Echobox](https://echobox.com)", "operator": "[Echobox](https://echobox.com)",
"respect": "Unclear at this time.", "respect": "Unclear at this time.",
@ -252,11 +280,11 @@
"respect": "No" "respect": "No"
}, },
"ICC-Crawler": { "ICC-Crawler": {
"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.",
"frequency": "No information.",
"function": "Scrapes data to train and support AI technologies.",
"operator": "[NICT](https://nict.go.jp)", "operator": "[NICT](https://nict.go.jp)",
"respect": "Yes" "respect": "Yes",
"function": "Scrapes data to train and support AI technologies.",
"frequency": "No information.",
"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": { "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. Our web intelligence products use this index to enable search and retrieval of similar images.",
@ -314,6 +342,13 @@
"frequency": "Unclear at this time.", "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" "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"
}, },
"MistralAI-User": {
"operator": "Mistral",
"respect": "Unclear at this time.",
"function": "AI Assistants",
"frequency": "Unclear at this time.",
"description": "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": { "MistralAI-User/1.0": {
"operator": "Mistral AI", "operator": "Mistral AI",
"function": "Takes action based on user prompts.", "function": "Takes action based on user prompts.",
@ -399,11 +434,11 @@
"description": "Crawls sites to surface as results in Perplexity." "description": "Crawls sites to surface as results in Perplexity."
}, },
"PetalBot": { "PetalBot": {
"description": "Operated by Huawei to provide search and AI assistant services.",
"frequency": "No explicit frequency provided.",
"function": "Used to provide recommendations in Hauwei assistant and AI search services.",
"operator": "[Huawei](https://huawei.com/)", "operator": "[Huawei](https://huawei.com/)",
"respect": "Yes" "respect": "Yes",
"function": "Used to provide recommendations in Hauwei assistant and AI search services.",
"frequency": "No explicit frequency provided.",
"description": "Operated by Huawei to provide search and AI assistant services."
}, },
"PhindBot": { "PhindBot": {
"description": "Company offers an AI agent that uses AI and generate extra web query on the fly", "description": "Company offers an AI agent that uses AI and generate extra web query on the fly",
@ -420,11 +455,11 @@
"respect": "Unclear at this time." "respect": "Unclear at this time."
}, },
"QualifiedBot": { "QualifiedBot": {
"description": "Operated by Qualified as part of their suite of AI product offerings.",
"frequency": "No explicit frequency provided.",
"function": "Company offers AI agents and other related products; usage can be assumed to support said products.",
"operator": "[Qualified](https://www.qualified.com)", "operator": "[Qualified](https://www.qualified.com)",
"respect": "Unclear at this time." "respect": "Unclear at this time.",
"function": "Company offers AI agents and other related products; usage can be assumed to support said products.",
"frequency": "No explicit frequency provided.",
"description": "Operated by Qualified as part of their suite of AI product offerings."
}, },
"QuillBot": { "QuillBot": {
"description": "Operated by QuillBot as part of their suite of AI product offerings.", "description": "Operated by QuillBot as part of their suite of AI product offerings.",
@ -524,6 +559,13 @@
"operator": "[Velen Crawler](https://velen.io)", "operator": "[Velen Crawler](https://velen.io)",
"respect": "[Yes](https://velen.io)" "respect": "[Yes](https://velen.io)"
}, },
"WARDBot": {
"operator": "WEBSPARK",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"frequency": "Unclear at this time.",
"description": "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": { "Webzio-Extended": {
"operator": "Unclear at this time.", "operator": "Unclear at this time.",
"respect": "Unclear at this time.", "respect": "Unclear at this time.",