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
18 repositories
Parses complex PDFs, scans and Office files into Markdown or JSON while keeping tables and formulas. Comes with a CLI, a Python SDK and an agent skill.
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.
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.
A framework and runtime for agent platforms: an SDK to build, AgentOS to serve agents as a service with an API, and a web UI to manage them. Your data stays with you.
OpenAI's lightweight SDK: agents, tools, handoffs between agents and guardrails. Few abstractions, so it is quick to learn.
Microsoft's SDK for embedding LLMs into C#, Python and Java apps: plugins, planning and agents. Fits a corporate .NET stack well.
Tooling for computer-use agents: drivers for several OSes, virtual machines and benchmarks for training and evaluation.
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.
An SDK that drives the browser with a mix of code and natural language: extract data and click through any site without brittle selectors.
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.
A Python framework for real-time voice and multimodal agents: compose a speech-model-speech pipeline from modules. Client SDKs for web and mobile included.
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.
The official Python SDK for running Claude Code as a library: the agent loop, file and shell tools, MCP. The CLI ships bundled inside the package.
An OpenTelemetry-based toolkit that automatically traces calls to models, vector databases and frameworks. Data can go to any compatible monitoring system.
An SDK for observing agents: it records sessions, tracks cost and shows the chain of steps. Integrates with CrewAI, LangChain, OpenAI Agents SDK and others.
The official Go SDK for MCP, maintained together with Google. A server is built from `mcp.Server`, tools and a transport.
An observability platform from the makers of Pydantic: it traces plain code, model calls and agents. Built on OpenTelemetry, with an open-source SDK.
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.