ai.robots.txt/robots.json

{
    "AI2Bot": {
        "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"
    },
    "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"
    },
    "Amazonbot": {
        "description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses.",
        "frequency": "No information. provided.",
        "function": "Service improvement and enabling answers for Alexa users.",
        "operator": "Amazon",
        "respect": "Yes"
    },
    "Applebot": {
        "description": "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",
        "frequency": "Unclear at this time.",
        "function": "AI Search Crawlers",
        "operator": "Unclear at this time.",
        "respect": "Unclear at this time."
    },
    "Applebot-Extended": {
        "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.",
        "frequency": "Unclear at this time.",
        "function": "Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others.",
        "operator": "[Apple](https://support.apple.com/en-us/119829#datausage)",
        "respect": "Yes"
    },
    "Bytespider": {
        "description": "Downloads data to train LLMS, including ChatGPT competitors.",
        "frequency": "Unclear at this time.",
        "function": "LLM training.",
        "operator": "ByteDance",
        "respect": "No"
    },
    "CCBot": {
        "description": "Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers).",
        "frequency": "Monthly at present.",
        "function": "Provides open crawl dataset, used for many purposes, including Machine Learning/AI.",
        "operator": "[Common Crawl Foundation](https://commoncrawl.org)",
        "respect": "[Yes](https://commoncrawl.org/ccbot)"
    },
    "ChatGPT-User": {
        "description": "Used by plugins in ChatGPT to answer queries based on user input.",
        "frequency": "Only when prompted by a user.",
        "function": "Takes action based on user prompts.",
        "operator": "[OpenAI](https://openai.com)",
        "respect": "Yes"
    },
    "Claude-Web": {
        "description": "Scrapes data to train LLMs and AI products offered by Anthropic.",
        "frequency": "No information. provided.",
        "function": "Scrapes data to train Anthropic's AI products.",
        "operator": "[Anthropic](https://www.anthropic.com)",
        "respect": "Unclear at this time."
    },
    "ClaudeBot": {
        "description": "Scrapes data to train LLMs and AI products offered by Anthropic.",
        "frequency": "No information. provided.",
        "function": "Scrapes data to train Anthropic's AI products.",
        "operator": "[Anthropic](https://www.anthropic.com)",
        "respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)"
    },
    "Diffbot": {
        "description": "Diffbot is an application used to parse web pages into structured data; this data is used for monitoring or AI model training.",
        "frequency": "Unclear at this time.",
        "function": "Aggregates structured web data for monitoring and AI model training.",
        "operator": "[Diffbot](https://www.diffbot.com/)",
        "respect": "At the discretion of Diffbot users."
    },
    "FacebookBot": {
        "description": "Officially used for training Meta \"speech recognition technology,\" unknown if used to train Meta AI specifically.",
        "frequency": "Up to 1 page per second",
        "function": "Training language models",
        "operator": "Meta/Facebook",
        "respect": "[Yes](https://developers.facebook.com/docs/sharing/bot/)"
    },
    "FriendlyCrawler": {
        "description": "Unclear who the operator is; but data is used for training/machine learning.",
        "frequency": "Unclear at this time.",
        "function": "We are using the data from the crawler to build datasets for machine learning experiments.",
        "operator": "Unknown",
        "respect": "[Yes](https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler)"
    },
    "GPTBot": {
        "description": "Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies.",
        "frequency": "No information.",
        "function": "Scrapes data to train OpenAI's products.",
        "operator": "[OpenAI](https://openai.com)",
        "respect": "Yes"
    },
    "Google-Extended": {
        "description": "Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search.",
        "frequency": "No information.",
        "function": "LLM training.",
        "operator": "Google",
        "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)"
    },
    "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)"
    },
    "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.\"",
        "frequency": "No information.",
        "function": "Scrapes data.",
        "operator": "Google",
        "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)"
    },
    "GoogleOther-Video": {
        "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)"
    },
    "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)",
        "respect": "Yes"
    },
    "ISSCyberRiskCrawler": {
        "description": "Used to train machine learning based models to quantify cyber risk.",
        "frequency": "No information.",
        "function": "Scrapes data to train machine learning models.",
        "operator": "[ISS-Corporate](https://iss-cyber.com)",
        "respect": "No"
    },
    "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.",
        "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",
        "operator": "[ImageSift](https://imagesift.com)",
        "respect": "[Yes](https://imagesift.com/about)"
    },
    "Kangaroo Bot": {
        "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",
        "frequency": "Unclear at this time.",
        "function": "AI Data Scrapers",
        "operator": "Unclear at this time.",
        "respect": "Unclear at this time."
    },
    "Meta-ExternalAgent": {
        "description": "\"The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly.\"",
        "frequency": "No information.",
        "function": "Used to train models and improve products.",
        "operator": "[Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers)",
        "respect": "Yes."
    },
    "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",
        "frequency": "Unclear at this time.",
        "function": "AI Assistants",
        "operator": "Unclear at this time.",
        "respect": "Unclear at this time."
    },
    "OAI-SearchBot": {
        "description": "Crawls sites to surface as results in SearchGPT.",
        "frequency": "No information.",
        "function": "Search result generation.",
        "operator": "[OpenAI](https://openai.com)",
        "respect": "[Yes](https://platform.openai.com/docs/bots)"
    },
    "PerplexityBot": {
        "description": "Operated by Perplexity to obtain results in response to user queries.",
        "frequency": "Takes action based on user prompts.",
        "function": "Used to answer queries at the request of users.",
        "operator": "[Perplexity](https://www.perplexity.ai/)",
        "respect": "[No](https://www.macstories.net/stories/wired-confirms-perplexity-is-bypassing-efforts-by-websites-to-block-its-web-crawler/)"
    },
    "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/)",
        "respect": "Yes"
    },
    "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.\"",
        "frequency": "No information.",
        "function": "Scrapes data for a variety of uses including training AI.",
        "operator": "[Zyte](https://www.zyte.com)",
        "respect": "Unclear at this time."
    },
    "Sidetrade indexer bot": {
        "description": "AI product training.",
        "frequency": "No information.",
        "function": "Extracts data for a variety of uses including training AI.",
        "operator": "[Sidetrade](https://www.sidetrade.com)",
        "respect": "Unclear at this time."
    },
    "Timpibot": {
        "description": "Makes data available for training AI models.",
        "frequency": "No information.",
        "function": "Scrapes data for use in training LLMs.",
        "operator": "[Timpi](https://timpi.io)",
        "respect": "Unclear at this time."
    },
    "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)"
    },
    "Webzio-Extended": {
        "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",
        "frequency": "Unclear at this time.",
        "function": "AI Data Scrapers",
        "operator": "Unclear at this time.",
        "respect": "Unclear at this time."
    },
    "YouBot": {
        "description": "Retrieves data used for You.com web search engine and LLMs.",
        "frequency": "No information.",
        "function": "Scrapes data for search engine and LLMs.",
        "operator": "[You](https://about.you.com/youchat/)",
        "respect": "[Yes](https://about.you.com/youbot/)"
    },
    "anthropic-ai": {
        "description": "Scrapes data to train LLMs and AI products offered by Anthropic.",
        "frequency": "No information. provided.",
        "function": "Scrapes data to train Anthropic's AI products.",
        "operator": "[Anthropic](https://www.anthropic.com)",
        "respect": "Unclear at this time."
    },
    "cohere-ai": {
        "description": "Retrieves data based on user prompts.",
        "frequency": "Takes action based on user prompts.",
        "function": "Retrieves data to provide responses to user-initiated prompts.",
        "operator": "[Cohere](https://cohere.com)",
        "respect": "Unclear at this time."
    },
    "facebookexternalhit": {
        "description": "Unclear at this time.",
        "frequency": "Unclear at this time.",
        "function": "No information.",
        "operator": "Meta/Facebook",
        "respect": "[Yes](https://developers.facebook.com/docs/sharing/bot/)"
    },
    "iaskspider/2.0": {
        "description": "Used to provide answers to user queries.",
        "frequency": "Unclear at this time.",
        "function": "Crawls sites to provide answers to user queries.",
        "operator": "iAsk",
        "respect": "No"
    },
    "img2dataset": {
        "description": "Downloads large sets of images into datasets for LLM training or other purposes.",
        "frequency": "At the discretion of img2dataset users.",
        "function": "Scrapes images for use in LLMs.",
        "operator": "[img2dataset](https://github.com/rom1504/img2dataset)",
        "respect": "Unclear at this time."
    },
    "omgili": {
        "description": "Crawls sites for APIs used by Hootsuite, Sprinklr, NetBase, and other companies. Data also sold for research purposes or LLM training.",
        "frequency": "No information.",
        "function": "Data is sold.",
        "operator": "[Webz.io](https://webz.io/)",
        "respect": "[Yes](https://webz.io/blog/web-data/what-is-the-omgili-bot-and-why-is-it-crawling-your-website/)"
    },
    "omgilibot": {
        "description": "Legacy user agent initially used for Omgili search engine. Unknown if still used, `omgili` agent still used by Webz.io.",
        "frequency": "No information.",
        "function": "Data is sold.",
        "operator": "[Webz.io](https://webz.io/)",
        "respect": "[Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html)"
    }
}