# UnearthKit, policy of Oct 23, 2026: search engines, AI answer engines and AI model training allowed; Common Crawl and data resellers blocked

# Search engines and AI answer engines
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Meta-WebIndexer
User-agent: DuckAssistBot
User-agent: Amzn-SearchBot
User-agent: MistralAI-User
Allow: /

# AI assistant model training
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: xAI-Bot
User-agent: DeepseekBot
User-agent: cohere-ai
Allow: /

# Blocked: Common Crawl (archive redistributed to anyone) and data resellers
User-agent: CCBot
User-agent: Bytespider
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Timpibot
Disallow: /

# All other robots
User-agent: *
Allow: /

Sitemap: https://unearthkit.com/sitemap.xml