# robots.txt for www.beratung-rheinbach.de
# Last updated: 2026-01-24

User-agent: *
Allow: /
Disallow: /.github/
Disallow: /.phan/
Disallow: /assets/
Disallow: /backup/
Disallow: /bin/
Disallow: /cache/
Disallow: /logs/
Disallow: /system/
Disallow: /tests/
Disallow: /tmp/
Disallow: /user/
Disallow: /vendor/
Disallow: /webserver-configs/
Allow: /user/pages/
Allow: /user/themes/
Allow: /user/images/
Allow: *.css$
Allow: *.js$
Allow: /system/*.js$

# ===========================================
# AI/LLM Crawlers - Explicitly Allowed
# ===========================================

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

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

# Microsoft/Bing AI
User-agent: Bingbot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

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

# Amazon
User-agent: Amazonbot
Allow: /

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

# ===========================================
# LLM-optimized content available at:
# https://www.beratung-rheinbach.de/llms.txt
# https://www.beratung-rheinbach.de/.well-known/llms.txt
# https://www.beratung-rheinbach.de/llms-full.txt
# ===========================================

Sitemap: https://www.beratung-rheinbach.de/sitemap.xml