# namestrace robots policy
# Source-of-truth for crawler access. See docs/site-protections.md §4 for
# the rationale behind blocking AI-training crawlers while keeping search
# and ad crawlers fully open.

# ────────────────────────────────────────────────────────────────────
# 1. Google's search + ad crawlers — fully allowed.
#    Explicit rules so they're never accidentally caught by future
#    wildcard changes.
# ────────────────────────────────────────────────────────────────────

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: AdsBot-Google-Mobile
Allow: /

User-agent: Mediapartners-Google
Allow: /

# ────────────────────────────────────────────────────────────────────
# 2. All other search engines — fully allowed by default.
# ────────────────────────────────────────────────────────────────────

User-agent: *
Allow: /

# ────────────────────────────────────────────────────────────────────
# 3. AI / generative-model training crawlers — blocked.
#    Per /terms clause 4, site content may not be used to train,
#    fine-tune, benchmark, or evaluate machine-learning or generative
#    AI models. These specific User-agents override the wildcard above.
#    Note: Google-Extended is Google's AI-training crawler; it is
#    distinct from Googlebot (search) and AdsBot-Google (AdSense),
#    which remain allowed.
# ────────────────────────────────────────────────────────────────────

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: omgili
Disallow: /

Sitemap: https://namestrace.com/sitemap-index.xml