# robots.txt — tibornemeth.com
# Posture: allow live AI search bots, disallow AI training crawlers
# Updated: 2026-04-29
# ─── Default for traditional crawlers (Googlebot, Bingbot, etc.) ───
User-agent: *
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
# ─── AI training crawlers — DISALLOW ───
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Diffbot
Disallow: /
# ─── AI live/search crawlers — ALLOW (with same admin exclusions) ───
User-agent: OAI-SearchBot
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: ChatGPT-User
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: Claude-User
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: Claude-SearchBot
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: Claude-Web
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: PerplexityBot
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: Perplexity-User
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: DuckAssistBot
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
User-agent: Amazonbot
Disallow: /admin/
Disallow: /staging/
Disallow: /pdf/
# ─── Other ───
User-agent: MJ12bot
Crawl-delay: 5
Sitemap: https://tibornemeth.com/sitemap.xml