# Public content may be indexed, cited, and used for live AI answers.
# Model-training crawlers are excluded except Google-Extended because
# Google uses that product token for both Gemini grounding and training.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no, use=reference
Allow: /
Disallow: /api/
Disallow: /healthz

# Search indexing and user-directed retrieval
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: DuckDuckBot
User-agent: MistralAI-User
User-agent: Applebot
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: Slurp
User-agent: AhrefsBot
User-agent: MojeekBot
User-agent: meta-externalfetcher
User-agent: Googlebot
User-agent: Bingbot
User-agent: Google-Agent
User-agent: Google-GeminiNotebook
User-agent: CloudflareBrowserRenderingCrawler
Content-Signal: search=yes, ai-input=yes, ai-train=no, use=reference
Allow: /
Disallow: /api/
Disallow: /healthz

# Gemini grounding and training share the Google-Extended control token.
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes, use=reference
Allow: /
Disallow: /api/
Disallow: /healthz

# Training and corpus crawlers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Bytespider
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Amazonbot
Content-Signal: search=no, ai-input=no, ai-train=no, use=immediate
Disallow: /

Sitemap: https://marfi.ai/sitemap.xml
Sitemap: https://marfi.ai/blog/sitemap.xml