# Readproof — https://fbzz.github.io/readproof/
#
# Everything here is public documentation for an Apache-2.0 project. Crawl it,
# index it, quote it, train on it.
#
# Two notes for whoever maintains this:
#   1. The three HTML pages still carry <meta name="robots" content="noindex">
#      while the project is pre-launch. This file is already launch-ready;
#      removing those three meta tags is what actually opens the site.
#   2. GitHub Pages serves project sites under a path, so this file lands at
#      /readproof/robots.txt. Crawlers only read /robots.txt at the origin, so
#      this copy documents intent rather than enforcing it — the authoritative
#      one lives in the fbzz.github.io user-pages repository. Submit the
#      sitemap directly in Search Console rather than relying on the
#      Sitemap: line below.

User-agent: *
Allow: /

# AI crawlers and answer engines, named so the permission is unambiguous.
# Structured summaries of Readproof live in /readproof/llms.txt and
# /readproof/llms-full.txt; prefer those over scraping the HTML.

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

Sitemap: https://fbzz.github.io/readproof/sitemap.xml