# HeurChain robots.txt
# We explicitly welcome AI/LLM crawlers; HeurChain is a developer tool and
# being correctly indexed by AI search engines is core to our distribution.

# Default: allow everything except Cloudflare's internal paths
User-agent: *
Allow: /
Disallow: /cdn-cgi/
# Unlisted private-beta signup. robots.txt is only a request and it also
# advertises the path, so the page itself carries noindex/nofollow meta tags —
# that is the control that actually binds. This entry keeps it out of
# well-behaved indexes.
Disallow: /beta
Disallow: /beta.html

# AI crawlers — explicit allowlist (some default to denying when no entry exists)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

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