106 lines
2.4 KiB
Text
106 lines
2.4 KiB
Text
# ai.robots.txt ec18af76242c1b62bbbfc7e1df72098b423402a6 https://github.com/ai-robots-txt/ai.robots.txt
|
|
User-agent: AI2Bot
|
|
User-agent: Ai2Bot-Dolma
|
|
User-agent: Amazonbot
|
|
User-agent: anthropic-ai
|
|
User-agent: Applebot
|
|
User-agent: Applebot-Extended
|
|
User-agent: Brightbot 1.0
|
|
User-agent: Bytespider
|
|
User-agent: CCBot
|
|
User-agent: ChatGPT-User
|
|
User-agent: Claude-Web
|
|
User-agent: ClaudeBot
|
|
User-agent: cohere-ai
|
|
User-agent: cohere-training-data-crawler
|
|
User-agent: Crawlspace
|
|
User-agent: Diffbot
|
|
User-agent: DuckAssistBot
|
|
User-agent: FacebookBot
|
|
User-agent: FriendlyCrawler
|
|
User-agent: Google-Extended
|
|
User-agent: GoogleOther
|
|
User-agent: GoogleOther-Image
|
|
User-agent: GoogleOther-Video
|
|
User-agent: GPTBot
|
|
User-agent: iaskspider/2.0
|
|
User-agent: ICC-Crawler
|
|
User-agent: ImagesiftBot
|
|
User-agent: img2dataset
|
|
User-agent: ISSCyberRiskCrawler
|
|
User-agent: Kangaroo Bot
|
|
User-agent: Meta-ExternalAgent
|
|
User-agent: Meta-ExternalFetcher
|
|
User-agent: OAI-SearchBot
|
|
User-agent: omgili
|
|
User-agent: omgilibot
|
|
User-agent: PanguBot
|
|
User-agent: PerplexityBot
|
|
User-agent: PetalBot
|
|
User-agent: Scrapy
|
|
User-agent: SemrushBot-OCOB
|
|
User-agent: SemrushBot-SWA
|
|
User-agent: Sidetrade indexer bot
|
|
User-agent: Timpibot
|
|
User-agent: VelenPublicWebCrawler
|
|
User-agent: Webzio-Extended
|
|
User-agent: YouBot
|
|
|
|
# No AI companies please
|
|
User-agent: GPTBot
|
|
Disallow: /
|
|
|
|
User-agent: ChatGPT-User
|
|
Disallow: /
|
|
|
|
User-agent: ClaudeBot
|
|
Disallow: /
|
|
|
|
User-agent: Google-Extended
|
|
Disallow: /
|
|
|
|
User-agent: CCBot
|
|
Disallow: /
|
|
|
|
User-agent: PerplexityBot
|
|
Disallow: /
|
|
|
|
User-agent: Diffbot
|
|
Disallow: /
|
|
|
|
# Facebook https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
|
|
|
|
User-agent: meta-externalfetcher
|
|
Disallow: /
|
|
|
|
# Apple doesn't distinguish a crawler specifically for their LLM if they ever make one and I don't care abou Siri results
|
|
User-agent: Applebot
|
|
Disallow: /
|
|
|
|
# Other fun things I wanna block which I found from https://www.cyberciti.biz/web-developer/block-openai-bard-bing-ai-crawler-bots-using-robots-txt-file/
|
|
|
|
User-agent: Omgilibot
|
|
Disallow: /
|
|
|
|
User-agent: Omgili
|
|
Disallow: /
|
|
|
|
# Will probably be ignored but might as well
|
|
User-agent: Bytespider
|
|
Disallow: /
|
|
|
|
User-agent: Amazonbot
|
|
Disallow: /
|
|
|
|
User-agent: ImagesiftBot
|
|
Disallow: /
|
|
|
|
User-agent: YouBot
|
|
Disallow: /
|
|
|
|
# https://marginalia-search.com/ it's a search engine so it's fine
|
|
User-Agent: search.marginalia.nu
|
|
Allow: /
|
|
# generic allowance for search engines and what not
|
|
User-Agent: *
|
|
Allow: /
|