# ══════════════════════════════════════════════════════════
# AI Pirates — robots.txt
# Letzte Aktualisierung: 2026-06-01
# ══════════════════════════════════════════════════════════

# Standard: Alle Crawler dürfen die Site indexieren
User-agent: *
Allow: /
Allow: /assets/chat-agent/widget.js
Disallow: /assets/chat-agent/api.php
Disallow: /assets/chat-agent/config.php
Disallow: /assets/chat-agent/data/
Disallow: /assets/llm-checker/api.php
Disallow: /assets/llm-checker/config.php
Disallow: /assets/llm-checker/data/
Disallow: /assets/llm-checker/weekly-report.php

# ──────────────────────────────────────────────────────────
# AI-Search & LLM-Training Crawler (explizit erlaubt)
# Wir wollen in ChatGPT, Claude, Perplexity, Gemini etc. sichtbar sein.
# ──────────────────────────────────────────────────────────

# OpenAI (ChatGPT Search + Browsing)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

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

User-agent: GoogleOther
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (Trainingsdaten-Basis für viele LLMs)
User-agent: CCBot
Allow: /

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

User-agent: Applebot-Extended
Allow: /

# Meta (Llama-Training, Meta AI)
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

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

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

# DuckDuckGo
User-agent: DuckAssistBot
Allow: /

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

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

# Diffbot (für AI-Knowledge-Graphs)
User-agent: Diffbot
Allow: /

# Sitemaps
Sitemap: https://www.ai-pirates.com/sitemap.xml
Sitemap: https://www.ai-pirates.com/sitemap-glossar.xml