# SaucesOnly robots.txt
# Full policy: https://saucesonly.com/ai.json

# ===== Standard search engines =====
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# ===== AI search & citation crawlers (ALLOWED) =====
# These bots index content for AI-powered search results with citations.

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

# ===== AI training crawlers (DISALLOWED) =====
# These bots scrape content to train foundation models.
# We do not permit our content to be used for model training without permission.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: omgili
Disallow: /

# ===== Default =====
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /auth
Disallow: /reset-password
Disallow: /profile
Disallow: /my-ratings
Disallow: /my-comments
Disallow: /saved-recipes

Sitemap: https://saucesonly.com/sitemap.xml