# AI Crawler Index — policy: block-ai-training
# Block AI training, keep AI search
# Refuse the crawlers that feed model training. Keep the ones that put you in ChatGPT, Claude, Perplexity and Gemini answers.
# Generated 2026-09-01 from https://www.pathwren.workers.dev/policy/block-ai-training.html
# 13 crawlers named. Paste into robots.txt at your document root.

User-agent: anthropic-ai   # control token, no crawler uses this user-agent
Disallow: /

User-agent: Applebot-Extended   # control token, no crawler uses this user-agent
Disallow: /

User-agent: Bytespider   # compliance disputed; enforce at the edge
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Google-Extended   # control token, no crawler uses this user-agent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /

User-agent: TikTokSpider   # compliance disputed; enforce at the edge
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: *
Allow: /

Sitemap: https://www.pathwren.workers.dev/sitemap.xml