# Standard crawlers
User-agent: *
Allow: /
Disallow: /api/

# ── AI Search & LLM Crawlers — explicitly welcome ─────────────────────────────

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Google AI (Gemini, AI Overviews, SGE)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Googlebot
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Claude-SearchBot (added May 2026 — separate UA for search-specific crawls)
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Meta (LLaMA training + AI features)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Apple (Siri, Spotlight, Apple Intelligence)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Microsoft (Bing AI, Copilot)
User-agent: bingbot
Allow: /

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

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

# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /

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

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

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

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

# Meta AI (Facebook / Instagram / WhatsApp / Meta AI assistant — 3B+ users)
User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Naver (Korean AI search)
User-agent: Yeti
Allow: /

User-agent: NaverBot
Allow: /

# Seznam (Czech AI search)
User-agent: SeznamBot
Allow: /

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

# Diffbot (used by Bing AI + many B2B AI services)
User-agent: Diffbot
Allow: /

# Sitemaps + AI-specific manifest files for explicit discovery
Sitemap: https://nemosapp.com/sitemap.xml