# Content Signals (contentsignals.org, draft-romm-aipref-contentsignals)
# Search, AI-assistant citation, and model training: all yes.
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# AI search crawlers - explicitly allowed
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

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

# Claude web-search index crawler + user-initiated fetch (what powers Claude's
# answers/citations — distinct from ClaudeBot, which is training only).
User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

# Perplexity user-initiated fetch (distinct from PerplexityBot).
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Training crawlers - allowed
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

# Opt-out signals for Google and Apple AI training crawlers
# Both honor the dedicated User-agent string for opt-out preferences.
# We allow them: change Allow to Disallow if you want to opt out of model training.
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

Sitemap: https://ownkube.io/sitemap-index.xml

# Agent-friendly indices (llmstxt.org)
# llms.txt: https://ownkube.io/llms.txt
# llms-full.txt: https://ownkube.io/llms-full.txt