A skills set and methodology for coding agents: clarify the task, plan, write tests, then code. The agent works with more discipline.
The AI movement's repository database
The best AI repositories
224 living projects — from agent frameworks to prompt-injection defense. Each comes with our own note: why it matters, who it is for and how to start in three steps.
Stars, forks and activity refresh daily via the GitHub API · updated October 6, 2026
- repositories
- 224
- categories
- 11
- stars in total
- 11M
- new stars in 30 days
- +235K
Last 30 days
Growing fastest
The most new stars over the last 30 days.
A service that turns any website into clean Markdown or structured data for models. It can search, scrape, crawl a whole site and even click through a page.
A small Microsoft utility that converts PDF, Word, PowerPoint, Excel and other files into Markdown that is easy to hand to a language model.
An open coding agent for the terminal with a desktop app. It is not tied to one provider: plug in whichever models you have.
A toolkit for spec-driven development: principles and a spec first, then a plan and tasks, and only then code. Works with several coding agents.
OpenAI's lightweight coding agent that runs in the terminal and works on your project's code. Written in Rust.
Categories
Agent frameworksFrameworks and orchestration: what agents and multi-agent systems are built from.23 repositoriesCoding agents & CLIAgents that write code in the terminal and editor, and the methods for working with them.21 repositoriesMCPThe Model Context Protocol spec, official SDKs and the best servers.20 repositoriesOpen models & inferenceOpen weights, local runs, fast inference and fine-tuning.38 repositoriesRAG & vector DBsSearch over your own data: document parsing, crawlers, vector databases, knowledge graphs.19 repositoriesEvals & observabilityHow to measure a model or agent and see what happens inside it.17 repositoriesPrompting & contextPrompts, structured output, skills and context engineering.16 repositoriesVoice, video, multimodalSpeech recognition and synthesis, voice agents, images and video.19 repositoriesAutomationNo-code workflows, browser and computer-use agents.15 repositoriesAwesome lists & learningCourses, books and awesome lists worth starting with.21 repositoriesSecurityPrompt injection, guardrails, red teaming and agent scanners.15 repositoriesMissing your favorite?Suggest a repository — we will review it and add it if it earns a spot.Suggest a repo →
Catalog
38 repositories
A self-hosted ChatGPT-style interface that connects to Ollama and any OpenAI-compatible API. Installs with a single Docker command and runs on your own server.
A C/C++ engine that runs language models on ordinary hardware: laptops, phones, GPU-less servers. Much of local AI, Ollama included, is built on it.
The largest community-curated list of MCP servers, sorted by category from databases to browsers. The place to look for an existing server before writing your own.
A ready-made RAG engine with a UI: it parses documents with templates, chunks them, searches with citations and supports agentic retrieval. Deploys with Docker.
Reference MCP servers from the protocol team: memory, git, filesystem and more. A solid pattern for how a server is built and a ready set to start with.
An open AI-developer platform: the agent writes code, runs commands and browses the web. Runs locally or on a shared server for a team.
Feeds fresh, version-specific library docs into the prompt so the model stops inventing outdated APIs. Works as an MCP server or through a CLI with a skill.
A single gateway to 100+ LLM providers in OpenAI format: a Python SDK and a proxy server with cost tracking, load balancing and logging. Swap models without changing code.
Hands Chrome DevTools to an agent: network, console, performance, screenshots. The agent does not just click, it sees why a page is slow or broken.
A long-running builder of "agents" that watch the web and events and act on your behalf: send emails, collect data, trigger chains. Runs on your own server.
A local replacement for cloud APIs: an OpenAI-compatible server that runs text, voice and image models on any hardware, no GPU required.
Meta's classic library for fast similarity search and clustering of vectors. It is not a database but an index engine that many other systems are built on.
A lightweight alternative to GraphRAG: it builds a knowledge graph from documents and answers questions using both the graph and plain vector search. Ships with a server and a web UI.
An open platform for training, serving and evaluating chat models. It produced Vicuna and runs Chatbot Arena, where people blind-compare model answers.
A Playwright-based MCP server that lets an agent drive a browser through page structure rather than screenshots. Good for testing sites and automating web actions.
GitHub's official MCP server: an agent reads repositories, issues and pull requests and works with them. Comes as a hosted version from GitHub and a local one in Docker.
An open text-to-speech model with multilingual synthesis and voice cloning. Comes with docs, a Docker image and a server mode.
A toolkit for coding agents that works with code semantically: finds symbols and references and edits through language servers instead of rereading whole files. Saves context on large projects.
The easiest vector database to start with: it runs inside your app process, stores documents and finds similar ones. Great for prototypes, with a client-server mode and a cloud.
An orchestration and scheduling platform: workflows are declared in YAML and run on events or schedules. Fits data pipelines and AI integrations alike.
A Python framework that hides the protocol plumbing: a decorated function becomes an MCP tool. The shortest path from idea to a working server.
Formerly MemGPT: a platform for agents with long-term memory that learn from experience. Today it lives on as the Letta Code terminal client with a server mode.
An AI automation platform with a friendly UI. Its TypeScript "pieces" automatically become MCP servers usable from Claude Desktop, Cursor and others.
The official Python SDK for MCP, used to write both servers and clients. A server with a single tool fits in a couple dozen lines.
An experimental framework for an agent that builds itself: functions live in a database, load automatically and come with a dashboard. The author warns it is for ideas, not production. The project kicked off the 2023 wave of autonomous agents.
A free MCP course from Microsoft: from basics and security to first servers, with examples in C#, Java, JavaScript, Rust, Python and TypeScript.
Gives a coding agent the structure of a Figma design: layers, spacing, colors. The code ends up closer to the design than it would from a screenshot.
The official TypeScript SDK for MCP, split into server and client packages with optional adapters for Node, Express and Fastify.
An embedded search database, like SQLite for embeddings: it stores data in files and searches by keyword, vector and SQL. Handy for multimodal data.
A visual debugger for MCP servers: connect your server, browse its tools and call them by hand. Comes as a web UI, a CLI and a TUI.
Did we miss something?
Suggest a repository
Send a GitHub link and a few words on why it belongs here. Every suggestion is reviewed by hand — not everything gets in.