{
 "category": "ai-training",
 "label": "AI training crawlers",
 "description": "Collect pages in bulk so that a model can be trained or fine-tuned on them. Blocking these removes you from future training sets and changes nothing a user sees today.",
 "count": 13,
 "crawlers": [
  {
   "slug": "anthropic-ai",
   "name": "anthropic-ai",
   "operator": "Anthropic",
   "operator_slug": "anthropic",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "anthropic-ai",
   "user_agent_substring": "anthropic-ai",
   "user_agent_example": "(no live crawler currently identifies with this string)",
   "respects_robots_txt": "n-a",
   "respects_robots_txt_label": "control token only — no crawler",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "A legacy robots.txt token from before Anthropic consolidated on ClaudeBot. It is still widely present in robots.txt files and costs nothing to keep, but it is a control token rather than a bot you will see in logs.",
   "cost_of_blocking": "None. Nothing crawls under this name today; keeping the rule is harmless insurance.",
   "operator_docs": "https://support.anthropic.com/en/articles/8896518",
   "html_url": "https://www.pathwren.workers.dev/crawler/anthropic-ai.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/anthropic-ai.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "applebot-extended",
   "name": "Applebot-Extended",
   "operator": "Apple",
   "operator_slug": "apple",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "Applebot-Extended",
   "user_agent_substring": "(control token only — no crawler)",
   "user_agent_example": "(none: Applebot-Extended never appears as a user-agent)",
   "respects_robots_txt": "n-a",
   "respects_robots_txt_label": "control token only — no crawler",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Apple's counterpart to Google-Extended: a robots.txt token that withdraws consent for Apple Intelligence and Apple foundation-model training, without touching Applebot's search crawl.",
   "cost_of_blocking": "Excluded from Apple Intelligence training. Siri, Spotlight and Safari suggestions are unaffected.",
   "operator_docs": "https://support.apple.com/en-us/119829",
   "html_url": "https://www.pathwren.workers.dev/crawler/applebot-extended.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/applebot-extended.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "bytespider",
   "name": "Bytespider",
   "operator": "ByteDance",
   "operator_slug": "bytedance",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "Bytespider",
   "user_agent_substring": "Bytespider",
   "user_agent_example": "Mozilla/5.0 (Linux; Android 5.0) AppleWebKit/537.36 (KHTML, like Gecko) Mobile Safari/537.36 (compatible; Bytespider; spider-feedback@bytedance.com)",
   "respects_robots_txt": "disputed",
   "respects_robots_txt_label": "compliance disputed",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "ByteDance's crawler, associated with training data collection for Doubao and related models. Repeatedly reported by CDNs and site operators as the highest-volume AI crawler on the web and as inconsistent about robots.txt.",
   "cost_of_blocking": "Little to lose. If you want it gone, expect to block by user-agent at the edge rather than to ask politely in robots.txt.",
   "operator_docs": "https://www.bytespider.net/",
   "html_url": "https://www.pathwren.workers.dev/crawler/bytespider.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/bytespider.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "claudebot",
   "name": "ClaudeBot",
   "operator": "Anthropic",
   "operator_slug": "anthropic",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "ClaudeBot",
   "user_agent_substring": "ClaudeBot",
   "user_agent_example": "Mozilla/5.0 (compatible; ClaudeBot/1.0; +claudebot@anthropic.com)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Anthropic's bulk crawler, gathering pages that may be used to train Claude models.",
   "cost_of_blocking": "Content excluded from training data for future Claude models. No effect on Claude's ability to fetch a link a user gives it.",
   "operator_docs": "https://support.anthropic.com/en/articles/8896518",
   "html_url": "https://www.pathwren.workers.dev/crawler/claudebot.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/claudebot.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "cohere-training-data-crawler",
   "name": "cohere-training-data-crawler",
   "operator": "Cohere",
   "operator_slug": "cohere",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "cohere-training-data-crawler",
   "user_agent_substring": "cohere-training-data-crawler",
   "user_agent_example": "Mozilla/5.0 (compatible; cohere-training-data-crawler)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Cohere's separately-named bulk crawler for model training data, split out so consent for training and consent for retrieval can differ.",
   "cost_of_blocking": "Excluded from Cohere model training.",
   "operator_docs": "https://cohere.com/",
   "html_url": "https://www.pathwren.workers.dev/crawler/cohere-training-data-crawler.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/cohere-training-data-crawler.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "facebookbot",
   "name": "FacebookBot",
   "operator": "Meta",
   "operator_slug": "meta",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "FacebookBot",
   "user_agent_substring": "FacebookBot",
   "user_agent_example": "FacebookBot/1.0 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Meta's older speech- and language-corpus crawler, largely superseded by meta-externalagent but still listed as a valid robots token.",
   "cost_of_blocking": "Negligible today. Keep the rule; expect little traffic.",
   "operator_docs": "https://developers.facebook.com/docs/sharing/webmasters/web-crawlers",
   "html_url": "https://www.pathwren.workers.dev/crawler/facebookbot.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/facebookbot.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "google-extended",
   "name": "Google-Extended",
   "operator": "Google",
   "operator_slug": "google",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "Google-Extended",
   "user_agent_substring": "(control token only — no crawler)",
   "user_agent_example": "(none: Google-Extended never appears as a user-agent)",
   "respects_robots_txt": "n-a",
   "respects_robots_txt_label": "control token only — no crawler",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Not a crawler. A robots.txt token that tells Google whether pages Googlebot already fetched may be used to train and ground Gemini. You will never see it in an access log; disallowing it changes what Google does with content it fetched under a different name.",
   "cost_of_blocking": "You are excluded from Gemini grounding and Gemini training. Google Search ranking and indexing are explicitly unaffected. This is the cleanest 'no training, keep my search traffic' lever that exists.",
   "operator_docs": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
   "html_url": "https://www.pathwren.workers.dev/crawler/google-extended.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/google-extended.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "googleother",
   "name": "GoogleOther",
   "operator": "Google",
   "operator_slug": "google",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "GoogleOther",
   "user_agent_substring": "GoogleOther",
   "user_agent_example": "Mozilla/5.0 (compatible; GoogleOther)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "published-ranges",
   "verification_label": "published IP ranges",
   "published_ip_ranges_url": "https://developers.google.com/static/search/apis/ipranges/special-crawlers.json",
   "ip_ranges_endpoint": "https://www.pathwren.workers.dev/ip-ranges/google-special.json",
   "ipv4_prefix_count": 135,
   "ipv6_prefix_count": 135,
   "what_it_is": "A generic fetcher used by Google product teams for one-off crawls and research, including data collection that does not belong to Search.",
   "cost_of_blocking": "No effect on Search indexing. Blocks internal Google research and product fetches.",
   "operator_docs": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
   "html_url": "https://www.pathwren.workers.dev/crawler/googleother.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/googleother.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "gptbot",
   "name": "GPTBot",
   "operator": "OpenAI",
   "operator_slug": "openai",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "GPTBot",
   "user_agent_substring": "GPTBot",
   "user_agent_example": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.2; +https://openai.com/gptbot",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "published-ranges",
   "verification_label": "published IP ranges",
   "published_ip_ranges_url": "https://openai.com/gptbot.json",
   "ip_ranges_endpoint": "https://www.pathwren.workers.dev/ip-ranges/openai-gptbot.json",
   "ipv4_prefix_count": 21,
   "ipv6_prefix_count": 0,
   "what_it_is": "OpenAI's bulk crawler. Pages it fetches may be used to train future OpenAI foundation models. It is not the bot that puts you in ChatGPT's search results, and blocking it does not remove you from them.",
   "cost_of_blocking": "Your content is excluded from training data for future OpenAI models. No effect on ChatGPT search visibility, on citations, or on links a user pastes into ChatGPT.",
   "operator_docs": "https://platform.openai.com/docs/bots",
   "html_url": "https://www.pathwren.workers.dev/crawler/gptbot.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/gptbot.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "meta-externalagent",
   "name": "meta-externalagent",
   "operator": "Meta",
   "operator_slug": "meta",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "meta-externalagent",
   "user_agent_substring": "meta-externalagent",
   "user_agent_example": "meta-externalagent/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Meta's AI crawler, gathering training data for Llama and Meta AI. It replaced the older FacebookBot name for this purpose.",
   "cost_of_blocking": "Excluded from Meta AI training. Link previews on Facebook, Instagram and WhatsApp are unaffected — those are a different bot.",
   "operator_docs": "https://developers.facebook.com/docs/sharing/webmasters/web-crawlers",
   "html_url": "https://www.pathwren.workers.dev/crawler/meta-externalagent.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/meta-externalagent.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "semrushbot-ocob",
   "name": "SemrushBot-OCOB",
   "operator": "Semrush",
   "operator_slug": "semrush",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "SemrushBot-OCOB",
   "user_agent_substring": "SemrushBot-OCOB",
   "user_agent_example": "Mozilla/5.0 (compatible; SemrushBot-OCOB/1.0; +http://www.semrush.com/bot.html)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "reverse-dns",
   "verification_label": "reverse DNS",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Semrush's separately-tokenised crawler for its AI content tooling, split out so SEO crawling and AI reuse can be answered differently.",
   "cost_of_blocking": "Exclusion from Semrush's AI corpus, with its SEO crawl unaffected.",
   "operator_docs": "https://www.semrush.com/bot/",
   "html_url": "https://www.pathwren.workers.dev/crawler/semrushbot-ocob.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/semrushbot-ocob.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "tiktokspider",
   "name": "TikTokSpider",
   "operator": "ByteDance",
   "operator_slug": "bytedance",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "TikTokSpider",
   "user_agent_substring": "TikTokSpider",
   "user_agent_example": "Mozilla/5.0 (compatible; TikTokSpider; ttspider-feedback@tiktok.com)",
   "respects_robots_txt": "disputed",
   "respects_robots_txt_label": "compliance disputed",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "A second ByteDance crawler identifying with TikTok, collecting page content for the same family of models.",
   "cost_of_blocking": "Little to lose unless TikTok search referral matters to you.",
   "operator_docs": "https://www.bytespider.net/",
   "html_url": "https://www.pathwren.workers.dev/crawler/tiktokspider.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/tiktokspider.json",
   "last_reviewed": "2026-09-01"
  },
  {
   "slug": "webzio-extended",
   "name": "Webzio-Extended",
   "operator": "Webz.io",
   "operator_slug": "webz",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "Webzio-Extended",
   "user_agent_substring": "Webzio-Extended",
   "user_agent_example": "Mozilla/5.0 (compatible; Webzio-Extended/1.0)",
   "respects_robots_txt": "documented",
   "respects_robots_txt_label": "obeys robots.txt (documented)",
   "verification_method": "none",
   "verification_label": "no published verification method",
   "published_ip_ranges_url": null,
   "ip_ranges_endpoint": null,
   "ipv4_prefix_count": 0,
   "ipv6_prefix_count": 0,
   "what_it_is": "Webz.io's opt-out token specifically for AI training reuse, in the pattern Google and Apple established.",
   "cost_of_blocking": "Your content is excluded from the AI-training tier of Webz.io's product while ordinary collection continues.",
   "operator_docs": "https://webz.io/blog/machine-learning/",
   "html_url": "https://www.pathwren.workers.dev/crawler/webzio-extended.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/webzio-extended.json",
   "last_reviewed": "2026-09-01"
  }
 ]
}