# Codext GmbH - robots.txt
# https://codext.de
#
# Allow all standard search engines + explicit AI/LLM crawler allowlist
# for AI Search Optimization (Google AI Overviews, ChatGPT, Perplexity, Claude, etc.)

User-agent: *
Allow: /
Disallow: /private/
Disallow: /_codext/
Disallow: /api/

# ─── Standard search engines ──────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# ─── AI / LLM crawlers - explicitly allowed for AI Search Optimization ────
# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Apple AI
User-agent: Applebot-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Meta
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# Common Crawl (training data)
User-agent: CCBot
Allow: /

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

# Cohere
User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# ByteDance / TikTok
User-agent: Bytespider
Allow: /

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Diffbot (used by AI products incl. Bard/Gemini training)
User-agent: Diffbot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Sitemaps + LLM-friendly content map
Sitemap: https://codext.de/sitemap-index.xml