# ============================================
# Traditional Search Engines
# ============================================
User-agent: Googlebot
User-agent: Bingbot
Allow: /


# ============================================
# AI Crawlers — All Allowed (search + training)
# Maximum visibility for Found For AI brand exposure
# ============================================

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

# Anthropic
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
User-agent: anthropic-ai
Allow: /

# Google (search-side + training + user-driven)
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: Google-NotebookLM
Allow: /

# Perplexity
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /

# Apple (search + training)
User-agent: Applebot
User-agent: Applebot-Extended
Allow: /

# Brave
User-agent: Bravebot
Allow: /

# DuckDuckGo
User-agent: DuckAssistBot
Allow: /

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

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

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

# Cohere
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Common Crawl (feeds open-source LLM training)
User-agent: CCBot
Allow: /

# ByteDance
User-agent: Bytespider
Allow: /

# xAI / Grok
User-agent: GrokBot
User-agent: xAI-Grok
User-agent: Grok-DeepSearch
User-agent: Grok
User-agent: xAI
Allow: /


# ============================================
# Catchall — everything else allowed except admin
# ============================================
User-agent: *
Allow: /
Disallow: /admin
Content-Signal: ai-train=yes, search=yes, ai-input=yes


Sitemap: https://foundforai.com/sitemap.xml