# elephantcross.org: open to every crawler, human search and AI alike.
# Decided by Luca, 2026-09-07 ("yes is a no brainer"): the site's whole
# purpose is to be found and repeated, so search, retrieval and training are
# all granted. Each AI crawler is named with its own group because the
# agent-readiness checks want a rule per bot, not a wildcard. Content Signals
# per contentsignals.org. Cloudflare's managed robots.txt (which prepended a
# training block) is switched off in the zone; if a block list ever appears
# above this line again, that switch is back on.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# OpenAI: training, search and the assistant's own fetches
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google's AI (Gemini and grounding; Search itself uses Googlebot)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (feeds most open models), Meta, Amazon, Apple, ByteDance, DuckDuckGo, Mistral
User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

Sitemap: https://elephantcross.org/sitemap.xml