User-agent: *
Allow: /
# /out/ is human-facing retailer redirects, not content. Nothing to index.
Disallow: /out/

# Named explicitly so that a default-deny elsewhere in the stack is visible as a
# deliberate choice rather than an accident. These datasets exist to be read by
# assistants; blocking their crawlers would make the whole point unmeasurable.
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Google-CloudVertexBot
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: meta-externalagent
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Applebot-Extended
Allow: /
User-agent: CCBot
Allow: /
User-agent: Bingbot
Allow: /

Sitemap: https://referencesource.org/sitemap.xml