# People and search engines may read the site.
# Training crawlers are asked not to. Free HTML is still copyable by a person.
#
# One exception, and it is deliberate: /u. The U device is four functions,
# MIT, and it is meant to be taken. Every agent told to stay out below is
# told /u is open. The exact /u path and /u/ children are allowed, so the carve-out
# holds without repealing anything. Anyone may scrape it. That is the point.
User-agent: *
Content-Signal: search=yes, ai-input=no, ai-train=no
Allow: /u$
Allow: /u/
Allow: /

User-agent: GPTBot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: ChatGPT-User
Allow: /u$
Allow: /u/
Disallow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /u$
Allow: /u/
Disallow: /

User-agent: CCBot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: anthropic-ai
Allow: /u$
Allow: /u/
Disallow: /

User-agent: ClaudeBot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: Claude-Web
Allow: /u$
Allow: /u/
Disallow: /

User-agent: Bytespider
Allow: /u$
Allow: /u/
Disallow: /

User-agent: Amazonbot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: Applebot-Extended
Allow: /u$
Allow: /u/
Disallow: /

User-agent: meta-externalagent
Allow: /u$
Allow: /u/
Disallow: /

User-agent: FacebookBot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: Diffbot
Allow: /u$
Allow: /u/
Disallow: /

User-agent: omgili
Allow: /u$
Allow: /u/
Disallow: /

User-agent: omgilibot
Allow: /u$
Allow: /u/
Disallow: /

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