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
An open coding agent for the terminal with a desktop app. It is not tied to one provider: plug in whichever models you have.
An automation platform with a visual editor: connect services with blocks and add your own code or AI agents where needed. 400+ integrations, self-hostable.
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 workspace for building AI apps: agentic workflows, RAG pipelines and a choice of models and tools in one interface. Deploy in the cloud or self-host.
Anthropic's coding agent that lives in the terminal: it understands your project, edits files, runs commands and handles git from plain-language requests.
Google's open terminal agent: it connects Gemini to your codebase and can edit files, run commands and search the web.
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.
A platform where you assemble a team of AI agents, schedule them and get reports. Works with many models; deploy on Vercel or with Docker.
An autonomous coding agent in three forms: IDE extension, CLI and SDK. It can run in the background, on a schedule and from chat apps.
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.
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 Claude Code plugin that turns it into a team of specialised agents: autopilot, team-work modes, and a deep interview before a task.
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.
An open coding agent as a VS Code extension, JetBrains plugin and CLI. The repo is frozen: version 2.0.0 was the final release, and the code now serves as a reference.
An open platform that shows every model call: traces, cost, quality scores and prompt versions. Use it in the cloud or self-host it.
A collaborative workspace to build, deploy and monitor AI agents and workflows: chat on the left, visual builder on the right. Cloud, self-hosted and a macOS app.
A TypeScript framework for agents and AI apps: agents, workflows, memory and quality evaluation in one place. A good fit for Node-based web teams.
A terminal coding agent from the Qwen team, tuned for their models but open and configurable. A good way to try open models in practice.
An open agentic-engineering platform: CLI, IDE plugins and a cloud. One of the most popular open-source coding agents.
The AI SDK from the makers of Next.js: one TypeScript interface to models, streaming, tool calling and React hooks. Switching providers takes one line.
Twelve principles for building LLM apps good enough to put in customers' hands: own your prompts, own your context, small agents, explicit control flow.
A command-line tool for testing prompts and agents: describe cases in a config and compare models. Also does red teaming and vulnerability scanning. Plugs into CI.
An SDK that drives the browser with a mix of code and natural language: extract data and click through any site without brittle selectors.
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.
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.
Isolated cloud sandboxes where an agent can safely run code and commands. One SDK call gives the model its own small computer.
The official TypeScript SDK for MCP, split into server and client packages with optional adapters for Node, Express and Fastify.
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.