# Block AI crawlers and training bots
# Last updated: 2026-03-23

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

# Google AI (not regular Googlebot search)
User-agent: Google-Extended
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: GoogleOther-Image
Disallow: /

User-agent: GoogleOther-Video
Disallow: /

# Apple
User-agent: Applebot-Extended
Disallow: /

# Meta
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Common Crawl
User-agent: CCBot
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

# Other AI crawlers
User-agent: AI2Bot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: iaskspider
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: ISSCyberRiskCrawler
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: FriendlyCrawler
Disallow: /

# Allow legitimate search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: *
Allow: /