# Search engines - allowed
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: Baiduspider
Allow: /
User-agent: Naverbot
Allow: /
User-agent: Yeti
Allow: /
User-agent: Applebot
Allow: /
User-agent: archive.org_bot
Allow: /
# AI scrapers and training bots - blocked
User-agent: Amazonbot
Disallow: /
User-agent: Anchor Browser
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: Claude-SearchBot
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Google-CloudVertexBot
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: Manus Bot
Disallow: /
User-agent: MistralAI-User
Disallow: /
User-agent: Novellum AI Crawl
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: Perplexity-User
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: ProRataInc
Disallow: /
User-agent: Timpibotimpi
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Applebot-Extended
Disallow: /
# Everything else - blocked by default
User-agent: *
Disallow: /
# Sitemap
Sitemap: https://numodex.com/sitemap-index.xml