# robots.txt - kimoun.com
# Updated: 2026-06-09
# Strategy: max GEO visibility - public content allowed for all AI agents
# including model training (volontaire, posture pro-discoverability).
# llms.txt: https://kimoun.com/llms.txt
# llms-full.txt: https://kimoun.com/llms-full.txt

# --- General rule ---
User-agent: *
Allow: /

# Internal / non-content pages
Disallow: /bonjour/
Disallow: /docs/
Disallow: /categories/
Disallow: /en/_modals/
Disallow: /landing/
Disallow: /en/landing/

# Content Signals (draft-romm-aipref-contentsignals-00)
# ai-input=yes  : content usable as agent input
# ai-train=yes  : model training autorisé (cohérent avec les Allow ci-dessous
#                 sur GPTBot, Google-Extended, ClaudeBot, CCBot…)
# search=yes    : search indexing allowed
Content-Signal: ai-input=yes, ai-train=yes, search=yes

# --- AI crawlers - public content explicitly allowed ---
# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# OpenAI Search (SearchGPT / ChatGPT Search) — distinct de GPTBot
User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Meta
User-agent: FacebookBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Apple
User-agent: Applebot-Extended
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

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

# Mistral
User-agent: MistralBot
Allow: /

# xAI (Grok)
User-agent: xAI
Allow: /

# Bytedance
User-agent: Bytespider
Allow: /

# DuckDuckGo (Duck Assist AI)
User-agent: DuckAssistBot
Allow: /

# You.com (AI search + assistant)
User-agent: YouBot
Allow: /

# Huawei (Petal Search + AI, marché asiatique)
User-agent: PetalBot
Allow: /

# Diffbot (data extraction utilisée par plusieurs apps IA)
User-agent: Diffbot
Allow: /

# --- Sitemaps ---
Sitemap: https://kimoun.com/sitemap.xml