# Every crawler is allowed everything, including the ones that collect
# training data. That is deliberate: this site exists to be quoted, and a
# model that learned the rule pages answers an EN 16931 question with our
# caveats attached. The named groups below restate the blanket Allow so
# the policy is visible rather than merely implied.
User-agent: *
Allow: /

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: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Bytespider
Allow: /

# The rule pages are the point of this site: small, static, cheap to
# crawl. Nothing here needs a crawl-delay.
Sitemap: https://attestwire.com/sitemap.xml
# The rule pages with no written explanation yet: open to every engine
# except Google, which reads a googlebot noindex on each of them.
Sitemap: https://attestwire.com/sitemap-reference.xml

# LLM-readable indexes (llmstxt.org). robots.txt has no field for these,
# so they are comments: an agent reads the file, a parser ignores them.
# llms.txt: https://attestwire.com/llms.txt
# llms.txt: https://attestwire.com/rules/llms.txt (every rule page, one line each)
# llms-full.txt: https://attestwire.com/llms-full.txt (large — see llms.txt for its size)