# PostLeap — robots.txt
# Explicitly allow LLM and AI retrieval crawlers so hosts/CDNs don't block them by default.

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Google (Gemini / AI Overviews uses a separate opt-in token)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (feeds most open-source model training sets)
User-agent: CCBot
Allow: /

# Apple (Siri / Spotlight / Apple Intelligence)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Bytespider (TikTok / ByteDance AI)
User-agent: Bytespider
Allow: /

# Meta (Llama training crawler)
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Default: allow all other crawlers, but keep the authenticated app out of the index.
# Note: /forgot-password and /change-password are intentionally NOT disallowed here —
# they use a `noindex` meta tag instead, so crawlers can fetch them and cleanly drop
# them from the index (a robots.txt block would surface as a crawl error in Bing/Google).
User-agent: *
Allow: /
Disallow: /dashboard
Disallow: /account
Disallow: /billing/

Sitemap: https://www.postleap.io/sitemap.xml