# robots.txt — gera.services
# Last updated: 2026-04-03

# Allow all web crawlers
User-agent: *
Allow: /
Disallow: /legal/

# ── AI & LLM crawlers — explicitly allowed ──────────────────────────────────

# OpenAI / ChatGPT
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: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Google (standard + AI / Gemini)
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

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

User-agent: msnbot
Allow: /

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

# Common Crawl (used to train many LLMs)
User-agent: CCBot
Allow: /

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

# Facebook / Meta
User-agent: facebookexternalhit
Allow: /

User-agent: FacebookBot
Allow: /

# Twitter / X
User-agent: Twitterbot
Allow: /

# Apple / Siri / Applebot
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Amazon / Alexa
User-agent: Amazonbot
Allow: /

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

# AI search engines
User-agent: Phind
Allow: /

User-agent: AI2Bot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: ImagesiftBot
Allow: /

User-agent: Omgilibot
Allow: /

# ── Sitemaps ─────────────────────────────────────────────────────────────────
Sitemap: https://gera.services/sitemap.xml

# ── LLMs.txt (AI crawler index) ──────────────────────────────────────────────
# See: https://gera.services/llms.txt
# AI Plugin: https://gera.services/.well-known/ai-plugin.json