# robots.txt for static-html-for-ai
# Demonstrates Content Signals + per-bot allow rules for AI crawlers.
# Reference: https://contentsignals.org/

# Default: search and AI input allowed; AI training opt-in.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Google-CloudVertexBot
Allow: /

# Common Crawl (training corpora)
User-agent: CCBot
Allow: /

# Microsoft
User-agent: bingbot
Allow: /

# Meta
User-agent: meta-externalagent
Allow: /

User-agent: meta-externalfetcher
Allow: /

Sitemap: https://static-html-for-ai.mcgrory.workers.dev/sitemap.xml