# robots.txt for LLM to Doc

# Default: everything except the conversion API.
User-agent: *
Allow: /
Disallow: /api/
Crawl-delay: 1

# AI / answer-engine crawlers — explicitly allowed (Perplexity, ChatGPT
# search, Google AI Overviews, Claude, Bing Copilot, etc.), same policy.
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Bingbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: Bytespider
User-agent: Amazonbot
User-agent: DuckAssistBot
Allow: /
Disallow: /api/
Crawl-delay: 1

# Sitemap + AI-specific entry points
Sitemap: https://llm2doc.app/sitemap.xml

# llms.txt — emerging convention (llmstxt.org) for AI engines
# to find canonical content without crawling JS-rendered pages.
# Available at: https://llm2doc.app/llms.txt