# Default — everyone may crawl.
User-agent: *
Allow: /

# Explicit allows for AI crawlers and answer engines.
# Several of these only honor rules addressed to their exact user-agent.

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI training / Gemini grounding
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (feeds most open LLMs)
User-agent: CCBot
Allow: /

# ByteDance / Doubao
User-agent: Bytespider
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

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

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

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

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

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

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

# Diffbot (Perplexity / Bing partner)
User-agent: Diffbot
Allow: /

# Brave Search
User-agent: PetalBot
Allow: /

Sitemap: https://getomit.pro/sitemap.xml