User-agent: *
Allow: /
Disallow: /api/
Disallow: /auth/

# Google
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

# Bing
User-agent: Bingbot
Allow: /

# AI Crawlers — allow public indexing, block API routes
User-agent: GPTBot
Allow: /
Disallow: /api/

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

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

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

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

User-agent: anthropic-ai
Allow: /
Disallow: /api/

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

User-agent: meta-externalagent
Allow: /
Disallow: /api/

User-agent: FacebookBot
Allow: /
Disallow: /api/

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

User-agent: Amazonbot
Allow: /
Disallow: /api/

User-agent: DuckAssistBot
Allow: /
Disallow: /api/

User-agent: YouBot
Allow: /
Disallow: /api/

User-agent: Diffbot
Allow: /
Disallow: /api/

User-agent: Bytespider
Allow: /
Disallow: /api/

User-agent: cohere-ai
Allow: /
Disallow: /api/

# Google Gemini / Bard training crawler (separate from Googlebot search)
User-agent: Google-Extended
Allow: /
Disallow: /api/

# Common Crawl — used by many AI training corpora
User-agent: CCBot
Allow: /
Disallow: /api/

# Mistral
User-agent: MistralAI-User
Allow: /
Disallow: /api/

# You.com search
User-agent: YouBot
Allow: /
Disallow: /api/

# Webz.io
User-agent: omgili
Allow: /
Disallow: /api/

User-agent: omgilibot
Allow: /
Disallow: /api/

# Timpi
User-agent: Timpibot
Allow: /
Disallow: /api/

# Webhose
User-agent: webhose
Allow: /
Disallow: /api/

# Friendly host for the LLM-readable summary
# (linked from <link rel="alternate" type="text/plain" href="/llms.txt">)

Sitemap: https://portfolio.ceciltan.com/sitemap.xml