# LLM crawlers are being blocked.
# Source for user-agents: https://webmaster-zone.com/blog/ai-crawler-list-2025

# Block OpenAI
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: OAI-SearchBot
Disallow: /

# Block Anthropic
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: anthropic-ai
Disallow: /

# Block Google AI
User-agent: Google-Extended
Disallow: /

# Meta/LLaMA
# Blocking FacebookBot will prevent previews from working on the Facebook.
#User-agent: FacebookBot
#Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /

# ByteDance/TikTok
# They don't respect robots.txt so they have to be blocked at the server level.
User-agent: Bytespider
Disallow: /

# CommonCrawl
User-agent: CCBot
Disallow: /

# Data Scrapers
User-agent: Omgilibot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: img2dataset
Disallow: /

# AI Search Engines
# These are search tools, so blocking them might make the site hard to find.
#User-agent: PerplexityBot
#Disallow: /
#User-agent: Diffbot
#Disallow: /
#User-agent: YouBot
#Disallow: /
#User-agent: Applebot
#Disallow: /