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

# AI search crawlers - explicitly allowed for AI-grounded answers
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

# Microsoft Copilot (uses Bing index)
User-agent: bingbot
Allow: /

User-agent: msnbot
Allow: /

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

User-agent: Meta-ExternalFetcher
Allow: /

# Common Crawl - foundation dataset used by most LLM training pipelines
User-agent: CCBot
Allow: /

# Google Vertex AI / Gemini grounding
User-agent: Google-CloudVertexBot
Allow: /

# Alternate Anthropic identifier
User-agent: anthropic-ai
Allow: /

# Allen Institute for AI (academic LLM training)
User-agent: AI2Bot
Allow: /

# Diffbot - knowledge graph used by several AI systems
User-agent: Diffbot
Allow: /

# iAsk AI
User-agent: iaskspider
Allow: /

# Timpi knowledge graph
User-agent: Timpibot
Allow: /

# Friendly Crawler (open AI training data)
User-agent: FriendlyCrawler
Allow: /

Sitemap: https://rajuprasai.com.np/sitemap.xml

# AI agent discovery
# llms.txt: https://rajuprasai.com.np/llms.txt
# llms-full.txt: https://rajuprasai.com.np/llms-full.txt
# Agent skills: https://rajuprasai.com.np/.well-known/agent-skills/index.json