# Rhythm Word — robots.txt
# Search and answer agents are allowed; training-only crawlers are denied.
# Schema feeds and AI documentation are advertised below for agents.

# Default policy: allow crawling of public pages, deny internal endpoints.
User-agent: *
Allow: /
Disallow: /api/
Disallow: /s/

# Cloudflare Content Signals (proposed). Search and answer engines welcome;
# do not use this site as raw training data without permission.
Content-Signal: search=yes, ai-input=yes, ai-train=no

# Major search and answer agents — allowed.
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: Google-Extended
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: Claude-Web
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: Perplexity-User
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: Applebot
Allow: /
Disallow: /api/
Disallow: /s/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/
Disallow: /s/

# Training-only crawlers — denied.
User-agent: CCBot
Disallow: /

User-agent: ByteSpider
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: omgili
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# Sitemap and structured data feed advertisement.
Sitemap: https://rhythmword.com/sitemap.xml

# NLWeb-style schema feed — points agents at our LLM-friendly indexes.
Schemamap: https://rhythmword.com/llms.txt
Schemamap: https://rhythmword.com/llms-full.txt
Schemamap: https://rhythmword.com/blog/llms.txt