# robots.txt for boostaro.org
# Last updated: March 2026

User-agent: *
Allow: /
Allow: /ai/
Allow: /.well-known/
Disallow: /cgi-bin/
Sitemap: https://boostaro.org/sitemap.xml

# =============================================
# AI Search Engine Crawlers - EXPLICITLY ALLOWED
# =============================================

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

User-agent: ChatGPT-User
Allow: /

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

# Perplexity
User-agent: PerplexityBot
Allow: /

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

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

User-agent: ClaudeBot
Allow: /

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

# ByteDance AI
User-agent: Bytespider
Allow: /

# Common Crawl (feeds many AI training sets)
User-agent: CCBot
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon AI
User-agent: Amazonbot
Allow: /

# Microsoft / Bing AI (Copilot)
User-agent: Bingbot
Allow: /

# =============================================
# Block SEO scraper bots (not useful, waste bandwidth)
# =============================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: serpstatbot
Disallow: /