More and more developer tools are adopting the llms.txt standard to build AI-friendly versions of their docs. The problem is that it's very hard to search across them. So I crawled millions of webpages to build Statespace, a search engine for llms.txt sites. And it's free, no API keys required.You can run plain queries to search across all sites: mcp server setup vector database embeddings oauth2 refresh token Or scope your queries to a specific site with "site: query" stripe: webhook verification mistral.ai: function calling docs.supabase.com: edge functions auth Quotes work like Google for exact phrases: "context window limit" vector database "semantic search" stripe: "webhook signature verification" This is still a work in progress, so looking for feedback and beta testers! Search for humans (website): https://statespace.com/ Search for agents (CLI, SDK, MCP, skill): https://github.com/statespace-tech/statespace Comments URL: https://news.ycombinator.com/item?id=47936303 Points: 2 #...