# Content signals (contentsignals.org): search and answers yes, model training no (see /terms)
Content-Signal: search=yes, ai-input=yes, ai-train=no

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /search
Disallow: /feedback
Disallow: /account
Disallow: /admin
Disallow: /pay/
Disallow: /_md/
Disallow: /api/v1/

# AI search and assistants are welcome under the rules above: see /llms.txt, /llms-full.txt, /auth.md, /api and
# /.well-known/api-catalog. Crawlers that collect training data are not (owner 2026-10-12; also blocked at the edge).
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: cohere-training-data-crawler
User-agent: AI2Bot
User-agent: Diffbot
User-agent: Timpibot
User-agent: omgilibot
User-agent: PanguBot
Disallow: /

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