The llms.txt hub is a comprehensive directory and resource collection built around the llms.txt standard, a proposed specification for providing AI-ready documentation to language models and AI-powered tools. Hosted at llmstxthub.com and maintained primarily by thedaviddias, the repository serves as the largest known directory of projects implementing this standard. The project is built with TypeScript and Next.js, leveraging Supabase for authentication and Tailwind CSS for styling, making it a modern web application designed to aggregate and showcase llms.txt implementations across the developer ecosystem.
The core purpose of the repository is to establish a central hub where developers can discover how various projects and platforms are adopting the llms.txt standard. The standard itself addresses a specific need in the AI development landscape: providing a structured way for LLM-powered tools and services to understand how to interact with project documentation and codebases. By implementing llms.txt files, projects can guide AI models on proper interpretation of their documentation, standardize how LLM-powered tools access information, improve the accuracy of AI-generated responses about their projects, and establish clear boundaries for AI interaction with their content.
The repository organizes its collection of implementations into multiple categories. Primary categories include AI and ML tools, developer tools, data and analytics platforms, integration and automation services, infrastructure and cloud solutions, and security and identity services. Secondary categorization further segments projects by use case, including personal projects, agency services, e-commerce platforms, educational resources, media companies, international projects, and miscellaneous implementations. This multi-layered organizational structure helps users navigate the growing directory of llms.txt implementations.
Beyond the directory itself, the project has spawned several complementary developer tools that extend the utility of the llms.txt standard. These include a Chrome extension for checking whether websites implement llms.txt files, a VS Code extension for searching and exploring llms.txt implementations directly within the editor, an MCP Explorer for analyzing llms.txt files using the Model Context Protocol, a Raycast extension for quick access within that application, an llms.txt Generator tool for creating llms.txt files from sitemaps and crawled pages, and a command-line interface package that can install llms.txt documentation as skills into over 35 AI coding agents.
GitGenius activity tracking shows that the repository maintains active development with 19 tracked issues and pull requests. The median response latency for these items is zero hours, indicating rapid engagement, though the mean response time of 102.1 hours reflects some variation in handling. Bug reports and enhancement requests represent the most common issue types, with 8 and 7 instances respectively. The primary maintainer thedaviddias accounts for 30 tracked events, with secondary contributors KlementMultiverse and NyllRE each contributing 2 events. The repository shares contributors with related projects including anomalyco/opencode, vercel/next.js, and mastra-ai/mastra, suggesting integration within a broader ecosystem of AI development tools and frameworks.
