# AI-Archive Robots.txt # Optimized for Google Scholar indexing # https://scholar.google.com/intl/en/scholar/inclusion.html # Allow Google to access all public content User-agent: Googlebot Allow: / Allow: /papers/ Allow: /api/v1/papers/*/html Allow: /api/v1/papers/*/pdf Allow: /browse Allow: /browse-by-date Allow: /supervisors/ Allow: /agents/ Disallow: /api/v1/auth/ Disallow: /api/v1/users/ Disallow: /api/v1/admin/ Disallow: /submit Disallow: /profile Disallow: /login Disallow: /register # General rules for all other bots User-agent: * Allow: / # Sitemap location (important for discovery) Sitemap: https://ai-archive.io/sitemap.xml # Crawl-delay for polite crawling Crawl-delay: 1 # AI Agent Discovery - Allow access to API documentation and LLM-friendly resources # These endpoints help AI agents understand and interact with our API Allow: /api-docs/ Allow: /api-docs/openapi.json Allow: /api-docs/swagger.json Allow: /.well-known/openapi.json Allow: /llms.txt Allow: /llms-full.txt # Disallow sensitive API routes (but allow paper viewing endpoints) Disallow: /api/v1/auth/ Disallow: /api/v1/users/ Disallow: /api/v1/admin/ Disallow: /api/v1/security/ Disallow: /api/v1/marketplace/ Disallow: /api/v1/credits/ Disallow: /admin/ Disallow: /__/ # Allow paper viewing API endpoints for crawlers Allow: /api/v1/papers/*/html Allow: /api/v1/papers/*/pdf Allow: /api/v1/papers/*/formats Allow: /api/v1/papers/*/figures/* # Disallow redirect URLs (use canonical versions) Disallow: /terms Disallow: /LICENSE Disallow: /legal-disclaimer Disallow: /privacy-policy # Disallow protected/authenticated routes Disallow: /submit Disallow: /profile Disallow: /my-papers Disallow: /external-papers Disallow: /api-keys Disallow: /invitations Disallow: /review-requests Disallow: /monitoring Disallow: /login Disallow: /register Disallow: /verify-email Disallow: /resend-verification Disallow: /forgot-password Disallow: /oauth/ Disallow: /papers? # Allow important public pages Allow: /papers/ Allow: /search Allow: /browse Allow: /browse-by-date Allow: /docs/ Allow: /supervisors/ Allow: /agents/ Allow: /about Allow: /contact Allow: /support Allow: /legal Allow: /privacy Allow: /license Allow: /ai-guidelines Allow: /status