# agent-coherence.dev — public marketing site for the agent-coherence OSS project.
# Discovery and AI indexing are encouraged. All major crawlers explicitly allowed,
# EXCEPT Yandex (disallowed below — Russia-affiliated; excluded per compliance policy).
#
# Content Signals (contentsignals.org): explicit, fully-permissive stance — search
# indexing, AI real-time answers (ai-input), and AI training (ai-train) are all
# granted. Maximum openness for discovery and citation. Crawlers that don't
# understand Content-Signal ignore it and still honor Allow: / below.

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

# --- Major search engines ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

# Yandex (Russia-affiliated) — excluded from indexing per compliance policy.
# "User-agent: Yandex" addresses the entire Yandex robot family per their docs.
User-agent: Yandex
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: Baiduspider
Allow: /

# --- AI training / retrieval crawlers (explicit opt-in) ---
# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (Gemini training is gated on this UA, separate from Googlebot search)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Common Crawl (powers many open-source LLMs)
User-agent: CCBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# ByteDance
User-agent: Bytespider
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

Sitemap: https://agent-coherence.dev/sitemap.xml