# robots.txt - mennorode.nl
# AI crawlers explicitly allowed, grouped by provider. No duplicates.

# General rules - allow all other crawlers
User-agent: *
Allow: /

# --- AI crawlers: explicitly allowed ---

# OpenAI (ChatGPT, SearchGPT)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Google (Gemini / AI Overviews)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Mistral (Le Chat)
User-agent: MistralAI-User
Allow: /

# Apple (Apple Intelligence)
User-agent: Applebot-Extended
Allow: /

# Amazon (Alexa / shopping AI)
User-agent: Amazonbot
Allow: /

# Meta (Llama, Meta AI in WhatsApp / Instagram / Facebook)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# ByteDance (Doubao, TikTok AI)
User-agent: Bytespider
Allow: /

# DuckDuckGo (DuckAssist)
User-agent: DuckAssistBot
Allow: /

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

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

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

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

# Diffbot
User-agent: Diffbot
Allow: /

# --- Sitemap ---
Sitemap: https://www.mennorode.nl/sitemap.xml