# Kakunin — Robots Crawling Rules
# Last updated: 2026-05-23

User-agent: *
Allow: /
Allow: /docs
Allow: /blog
Allow: /pricing
Allow: /privacy
Allow: /terms
Allow: /.ai/
Allow: /.well-known/

# Block internal/admin paths
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/
Disallow: /.env*
Disallow: /secrets/
Disallow: /studio/

# Content Signals — AI content usage preferences (https://contentsignals.org/)
Content-Signal: ai-train=no, search=yes, ai-input=yes

# Explicit AI crawler allowlist — all receive full public access
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Applebot
Allow: /

User-agent: MistralBot
Allow: /

User-agent: CohereBot
Allow: /

User-agent: AmazonBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Search engine sitemaps
Sitemap: https://www.kakunin.ai/sitemap.xml
Sitemap: https://www.kakunin.ai/.ai/sitemap.json

# AI systems — additional discovery
Allow: /.ai/
Allow: /.ai/*
Allow: /llms.txt
Allow: /llms-full.txt

# Rate limiting for aggressive crawlers
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: DotBot
Crawl-delay: 5