# cavmir.com — welcome, crawlers.
# Search engines and AI assistants are explicitly allowed to crawl, index,
# and cite this site. Machine-readable site guide: https://cavmir.com/llms.txt
# Full-text version for AI assistants: https://cavmir.com/llms-full.txt

User-agent: *
Allow: /
# JSON endpoints and Cloudflare's email-protection stubs are not pages; keeping
# them uncrawled keeps them out of Search Console's "Not found (404)" report.
Disallow: /api/
Disallow: /cdn-cgi/
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# --- Search engines ---
# (Google uses the most specific matching group, so the disallows must be
# repeated here — a bare "Allow: /" group would override the * group.)
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /cdn-cgi/

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# --- AI assistants & AI crawlers (explicitly welcome) ---
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Bytespider
Allow: /

# --- Link preview fetchers ---
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

Sitemap: https://cavmir.com/sitemap.xml
Sitemap: https://cavmir.com/sitemap-images.xml