# Madison Meds — robots.txt
# Last updated: 2026-04-18

# ============================================
# Traditional 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: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Applebot
Allow: /

# ============================================
# AI search engines & LLM crawlers
# (explicitly allowed — most default to disallowed unless opted in)
# ============================================

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Google AI Overviews, Gemini, Vertex AI
User-agent: Google-Extended
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

# Meta / Llama
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

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

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

# Amazon
User-agent: Amazonbot
Allow: /

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

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

# Bytedance
User-agent: Bytespider
Allow: /

# ============================================
# Default rule for any other bot
# ============================================
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /retatrutide.html
Disallow: /retatrutide
Disallow: /retatrutide-backup/
Disallow: /_retatrutide-backup/

# ============================================
# Sitemaps
# ============================================
Sitemap: https://madisonmeds.com/sitemap.xml

# LLM training/citation files
# Allow: /llms.txt
# Allow: /llms-full.txt