# RetentionCheck robots.txt
# Content-Signal (https://contentsignals.org) is emitted as an HTTP response
# header, not in robots.txt, so this file remains RFC 9309 valid.

# Default (all crawlers)
User-Agent: *
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*
Disallow: /welcome
Disallow: /_next/

# ============================================================
# AI search + training crawlers (explicit allowlist, 2026)
# ============================================================

# OpenAI
User-Agent: GPTBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

User-Agent: OAI-SearchBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

User-Agent: ChatGPT-User
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Anthropic Claude
User-Agent: ClaudeBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

User-Agent: Claude-Web
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

User-Agent: anthropic-ai
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Perplexity
User-Agent: PerplexityBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

User-Agent: Perplexity-User
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Google (AI Overviews, Gemini)
User-Agent: Google-Extended
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Apple Intelligence
User-Agent: Applebot-Extended
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Cohere
User-Agent: cohere-ai
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Meta / Facebook AI
User-Agent: Meta-ExternalAgent
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

User-Agent: FacebookBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# ByteDance (Doubao, etc.)
User-Agent: Bytespider
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Amazon
User-Agent: Amazonbot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# You.com
User-Agent: YouBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Diffbot
User-Agent: Diffbot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Mistral
User-Agent: MistralAI-User
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# Common Crawl (feeds many LLM training datasets)
User-Agent: CCBot
Allow: /
Disallow: /dashboard
Disallow: /api/
Disallow: /callback
Disallow: /settings
Disallow: /admin
Disallow: /*/opengraph-image
Disallow: /*/opengraph-image/*

# ============================================================
# Sitemaps + LLM indexes
# ============================================================
Sitemap: https://retentioncheck.com/sitemap.xml