From 6ce86768d4b2287c23754536e33fcf262578a0a5 Mon Sep 17 00:00:00 2001 From: hrbrmstr Date: Mon, 7 Sep 2026 10:09:24 -0400 Subject: chore: initial commit --- robots-tokens.txt | 151 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 151 insertions(+) create mode 100644 robots-tokens.txt (limited to 'robots-tokens.txt') diff --git a/robots-tokens.txt b/robots-tokens.txt new file mode 100644 index 0000000..377e147 --- /dev/null +++ b/robots-tokens.txt @@ -0,0 +1,151 @@ +# AI Crawler Index — robots.txt user-agent tokens, one per line, 2026-09-07 +# https://www.pathwren.workers.dev/data/robots-tokens.txt +AdsBot-Google +AdsBot-Google-Mobile +AdsBot-Google-Mobile-Apps +AhrefsBot +AhrefsSiteAudit +AI2Bot +Ai2Bot-Dolma +aiHitBot +AIWebIndex +Amazonbot +Andibot +Anomura +anthropic-ai +APIs-Google +Applebot +Applebot-Extended +archive.org_bot +atlassian-bot +AwarioRssBot +AwarioSmartBot +Baiduspider +barkrowler +bedrockbot +bingbot +Bytespider +CCBot +ChatGPT-User +Claude-SearchBot +Claude-User +Claude-Web +ClaudeBot +Cloudflare-AutoRAG +cohere-ai +cohere-training-data-crawler +Cotoyogi +Crawl4AI +Crawlspace +DataForSeoBot +Diffbot +dotbot +DuckAssistBot +DuckDuckBot +EchoboxBot +ExaSearchBot +FacebookBot +facebookexternalhit +Factset_spyderbot +FeedFetcher-Google +FirecrawlAgent +Google-Agent +Google-CloudVertexBot +Google-CWS +Google-Extended +Google-GeminiNotebook +Google-InspectionTool +Google-Pinpoint +Google-Read-Aloud +Google-Safety +Google-Site-Verification +Googlebot +Googlebot-Image +Googlebot-News +Googlebot-Video +GoogleMessages +GoogleOther +GoogleOther-Image +GoogleOther-Video +GoogleProducer +GPTBot +ia_archiver +ICC-Crawler +ImagesiftBot +img2dataset +ISSCyberRiskCrawler +Kagibot +KlaviyoAIBot +LAIONDownloader +Lightpanda +Linguee Bot +Mediapartners-Google +meta-externalagent +meta-externalfetcher +Meta-WebIndexer +MistralAI-User +MJ12bot +MojeekBot +OAI-SearchBot +omgili +omgilibot +panscient.com +Perplexity-User +PerplexityBot +PetalBot +PhindBot +Pinterestbot +Poseidon Research Crawler +QualifiedBot +QuillBot +Qwantbot +Qwantbot-news +Reflectionbot +rogerbot +SBIntuitionsBot +Scrapy +Screaming Frog SEO Spider +SemrushBot +SemrushBot-BA +SemrushBot-ESI +SemrushBot-FT +SemrushBot-OCOB +SemrushBot-SI +SemrushBot-SWA +SEOkicks +serpstatbot +SeznamBot +ShapBot +Sidetrade indexer bot +SiteAuditBot +Slackbot +Slackbot-LinkExpanding +SplitSignalBot +Storebot-Google +TerraCotta +Thinkbot +TikTokSpider +Timpibot +VelenPublicWebCrawler +Webzio-Extended +wpbot +YaK +YandexAdditional +YandexAdditionalBot +YandexBlogs +YandexBot +YandexCalendar +YandexComBot +YandexDirect +YandexFavicons +YandexImages +YandexMarket +YandexMedia +YandexMetrika +YandexMobileBot +YandexRenderResourcesBot +YandexScreenshotBot +YandexVideo +YandexWebmaster +Yeti +YouBot -- cgit v1.2.3