# NEXUS GEO — robots.txt
# Agence française de Generative Engine Optimization
# https://nexus-geo.fr
#
# Politique : nous sommes une agence GEO. Tous les bots IA légitimes
# sont EXPLICITEMENT BIENVENUS pour crawler, indexer et citer notre
# contenu. Seuls les crawlers abusifs ou non-respectueux sont bloqués.

User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /pilote
Disallow: /pilote/
Disallow: /api/

# === Moteurs de recherche classiques ===
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Applebot
Allow: /

# === Moteurs IA génératives — OpenAI ===
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# === Anthropic / Claude ===
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# === Perplexity ===
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# === Google Gemini / Vertex ===
User-agent: Google-Extended
Allow: /

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

# === Meta AI ===
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

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

User-agent: cohere-training-data-crawler
Allow: /

# === Mistral / Le Chat ===
User-agent: MistralAI-User
Allow: /

# === Amazon (Alexa, Nova, Q) ===
User-agent: Amazonbot
Allow: /

# === xAI / Grok ===
User-agent: xAI-Bot
Allow: /

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

# === Kagi ===
User-agent: Kagibot
Allow: /

# === DuckAssist ===
User-agent: DuckAssistBot
Allow: /

# === Diffbot ===
User-agent: Diffbot
Allow: /

# === Common Crawl ===
User-agent: CCBot
Allow: /

# === Petits acteurs IA légitimes ===
User-agent: PhindBot
Allow: /

User-agent: Andibot
Allow: /

User-agent: NeevaBot
Allow: /

# === Bots indésirables ===
User-agent: Bytespider
Disallow: /

User-agent: TimpiBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: PetalBot
Disallow: /

Sitemap: https://nexus-geo.fr/sitemap.xml

# Hints pour les LLM :
# - llms.txt      : https://nexus-geo.fr/llms.txt
# - llms-full.txt : https://nexus-geo.fr/llms-full.txt
# - ai.txt        : https://nexus-geo.fr/ai.txt