# Robots.txt for Celestia.org
# Optimized for AI/LLM crawlers and traditional search engines

# ——— OPENAI ———
# Search (shows webpages as links inside ChatGPT search) - NOT used for model training
User-agent: OAI-SearchBot
Allow: /

# User-driven browsing from ChatGPT and Custom GPTs - Acts after a human click
User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
Allow: /

# Model-training crawler - Allow for better representation in AI models
User-agent: GPTBot
Allow: /
Crawl-delay: 2

# ——— ANTHROPIC (Claude) ———
User-agent: anthropic-ai      # bulk model training
Allow: /
Crawl-delay: 2

User-agent: ClaudeBot         # chat citation fetch
User-agent: claude-web        # web-focused crawl
Allow: /

# ——— PERPLEXITY ———
User-agent: PerplexityBot     # index builder
Allow: /

User-agent: Perplexity-User   # human-triggered visit
Allow: /

# ——— GOOGLE (Gemini) ———
User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

# ——— MICROSOFT (Bing / Copilot) ———
User-agent: BingBot
Allow: /

# ——— AMAZON ———
User-agent: Amazonbot
Allow: /

# ——— APPLE ———
User-agent: Applebot
User-agent: Applebot-Extended
Allow: /

# ——— META ———
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: facebookexternalhit
Allow: /

# ——— LINKEDIN ———
User-agent: LinkedInBot
Allow: /

# ——— BYTEDANCE (TikTok) ———
User-agent: Bytespider
Allow: /

# ——— DUCKDUCKGO ———
User-agent: DuckAssistBot
Allow: /

# ——— OTHER AI/RESEARCH CRAWLERS ———
User-agent: AI2Bot
User-agent: CCBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: omgili
User-agent: YouBot
User-agent: MistralAI-User
Allow: /

# ——— DEFAULT FOR ALL OTHER CRAWLERS ———
User-agent: *
Allow: /
Crawl-delay: 1

# ——— SITEMAP LOCATION ———
Sitemap: https://celestia.org/sitemap.xml