User-agent: *
Allow: /

# OpenAI — ChatGPT browsing & search
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# OpenAI — Training crawler
User-agent: GPTBot
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

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

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

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

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

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

# Amazon — Alexa / Rufus / Nova
User-agent: Amazonbot
Allow: /

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

# ---------------------------------------------------------------
# AI scrapers — BLOCKED (low-value or aggressive scraping)
# ---------------------------------------------------------------
User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Diffbot
Disallow: /

Sitemap: https://www.getdefacto.com/sitemap.xml