# https://www.robotstxt.org/robotstxt.html
# Content Signals (https://contentsignals.org/): search and AI citation answers are allowed; bulk AI pre-training is prohibited.
# LLM indices: https://earlylore.com/llms.txt and https://earlylore.com/llms-full.txt
User-agent: *
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Allow: /api/v1/share/
Allow: /api/v1/screenshots/
Allow: /api/v1/icons/
Allow: /api/v1/avatars/
Disallow: /admin
Disallow: /*/admin
Disallow: /account
Disallow: /*/account
Disallow: /chats
Disallow: /*/chats
Disallow: /following
Disallow: /*/following
Disallow: /notes
Disallow: /*/notes
Disallow: /compare
Disallow: /*/compare
Disallow: /search
Disallow: /*/search
Disallow: /sign-in
Disallow: /*/sign-in
Disallow: /sign-up
Disallow: /*/sign-up
Disallow: /auth/
Disallow: /api/

# Block bulk AI pre-training crawlers & commercial dataset scrapers
User-agent: GPTBot
User-agent: CCBot
User-agent: Bytespider
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Diffbot
User-agent: DataForSeoBot
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: PetalBot
User-agent: BLEXBot
User-agent: Scrapy
Disallow: /

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