# Code Pathfinder - robots.txt
# Optimized for AI search discoverability (November 2025)
# https://codepathfinder.dev

# ============================================
# TRADITIONAL SEARCH ENGINES
# ============================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

# ============================================
# OPENAI CRAWLERS
# ============================================

# AI Search - shows pages as links in ChatGPT search (NOT for training)
User-agent: OAI-SearchBot
Allow: /

# User-triggered browsing from ChatGPT conversations
User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
Allow: /

# Model training crawler - Allow for better AI understanding of security tools
User-agent: GPTBot
Allow: /

# ============================================
# ANTHROPIC (CLAUDE) CRAWLERS
# ============================================

# Chat citation fetch - used when Claude cites sources
User-agent: ClaudeBot
Allow: /

# Web-focused crawl
User-agent: claude-web
Allow: /

# Model training - Allow for Claude to understand security scanning
User-agent: anthropic-ai
Allow: /

# ============================================
# PERPLEXITY CRAWLERS
# ============================================

# Index builder for Perplexity AI search
User-agent: PerplexityBot
Allow: /

# Human-triggered visits from Perplexity
User-agent: Perplexity-User
Allow: /

# ============================================
# GOOGLE AI (GEMINI)
# ============================================

# Controls access for Gemini AI training
User-agent: Google-Extended
Allow: /

# Google's agentic browser (Project Mariner)
User-agent: GoogleAgent-Mariner
Allow: /

# ============================================
# OTHER AI ASSISTANTS
# ============================================

# Amazon Alexa and Fire OS AI features
User-agent: Amazonbot
Allow: /

# Apple Siri and Spotlight
User-agent: Applebot
User-agent: Applebot-Extended
Allow: /

# Mistral AI (Le Chat assistant)
User-agent: MistralAI-User
Allow: /

# DuckDuckGo AI answers
User-agent: DuckAssistBot
Allow: /

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

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

# ============================================
# SOCIAL MEDIA CRAWLERS (for link previews)
# ============================================

User-agent: FacebookBot
User-agent: meta-externalagent
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: Bytespider
Allow: /

# ============================================
# RESEARCH & OPEN DATA CRAWLERS
# ============================================

# Academic research (Semantic Scholar)
User-agent: AI2Bot
Allow: /

# Common Crawl - open datasets for AI research
User-agent: CCBot
Allow: /

# Structured data extraction
User-agent: Diffbot
Allow: /

# Decentralized search
User-agent: Timpibot
Allow: /

# ============================================
# DEFAULT RULE
# ============================================

User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /private/

# ============================================
# SITEMAP
# ============================================

Sitemap: https://codepathfinder.dev/sitemap.xml

# ============================================
# LLM-READABLE CONTENT
# ============================================

# Machine-readable content for AI assistants
# Summary: https://codepathfinder.dev/llms.txt
# Full docs + all 190+ rules: https://codepathfinder.dev/llms-full.txt
# Per-rule markdown: https://codepathfinder.dev/registry/{language}/{category}/{rule-id}/md