# AI Crawlers from darkvisitors.com for ingestion into LLM training data without regard to copyright
User-agent: AI2Bot
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: cotoyogi
User-agent: Datenbank Crawler
User-agent: Diffbot
User-agent: FacebookBot
User-agent: Google-Extended
User-agent: GPTBot
User-agent: ICC-Crawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: netEstate Imprint Crawler
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: PanguBot
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Timpibot
User-agent: Webzio-Extended
User-agent: YouBot
Disallow: /

User-agent: *
# Only allow public-facing content and its assets
Allow: /api
Allow: /static
Allow: /insights
Allow: /projects
Allow: /folders
Disallow: /