# robots.txt — MOSFE Knowledge Repository
# https://www.yourdomain.com/robots.txt
# Last updated: 2026-06-23

# ============================================
# AI Crawler Access — EXPLICITLY ALLOWED
# ============================================

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

User-agent: ChatGPT-User
Allow: /

# Anthropic (ClaudeBot)
User-agent: ClaudeBot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Google AI (Gemini / Bard)
User-agent: Google-Extended
Allow: /

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

# Applebot (Apple Intelligence)
User-agent: Applebot
Allow: /

# Bytespider (ByteDance / TikTok AI)
User-agent: Bytespider
Allow: /

# ============================================
# Traditional Search Engine Crawlers
# ============================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ============================================
# Default Rules
# ============================================

User-agent: *
Allow: /
Disallow: /includes/
Disallow: /api/
Disallow: /admin/

# Sitemap location
Sitemap: https://mosfe.com/sitemap.xml