User-agent: *
Allow: /
Allow: /strain/
Allow: /brand/
Allow: /dispensary/
Allow: /grower/
Allow: /terpenes
Allow: /terpene/
Allow: /references
Allow: /references/
Allow: /wiki/

Disallow: /admin
Disallow: /moderate
Disallow: /account
Disallow: /scan
Disallow: /journal
Disallow: /user-entry/
Disallow: /setup
Disallow: /auth
Disallow: /signup
Disallow: /capture/
Disallow: /api/

# AI training / content-mining crawlers — disallowed across the entire
# site. Patient-submitted images and lab data on TerpTrace are
# copyrighted by their contributors; we do not consent to ingestion
# into model training corpora, embeddings, or commercial scrape
# products. Conventional search engines (Googlebot, Bingbot, etc.) are
# unaffected and continue to crawl under the rules above.
#
# Bot list maintained per the public consensus on opt-out user-agents
# (OpenAI, Anthropic, Google's separate AI crawl, Common Crawl, Apple,
# Perplexity, ByteDance, Cohere, Diffbot, Omgili, Meta). See /terms
# for the legal assertion of copyright + non-permissive use.

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

Sitemap: https://www.terptrace.com/sitemap.xml