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
48 repositories
A skills set and methodology for coding agents: clarify the task, plan, write tests, then code. The agent works with more discipline.
The core library for working with models: one codebase for text, vision, audio and multimodal tasks, for both inference and training. Most new open models ship through it.
The best-known toolkit for LLM apps: one interface to dozens of models, plus tools, chains and agents. You can swap providers without rewriting the app.
The foundation under most modern neural networks: GPU-accelerated tensors and automatic differentiation, wrapped in ordinary Python. Transformers, Llama and nearly every open model are written on it.
A unified framework for fine-tuning 100+ models with no code: through a config-driven CLI or the LLaMA Board web UI. Supports LoRA and other methods.
A multi-agent framework that plays out a whole software company: product manager, architect and engineer take roles and turn one sentence into a project together.
A high-level deep learning library that runs on top of JAX, TensorFlow or PyTorch: write a model once and pick the backend that suits the job.
Microsoft's framework for agents that talk to each other. It has the high-level AgentChat API and AutoGen Studio, a no-code graphical interface.
A framework where agents get roles, goals and tasks and work like a small team. The mental model is simple: crew, roles, process.
An agile AI-driven development method: a set of role agents (analyst, architect, developer and more) and a process from idea to code. Installs as skills or a plugin.
A framework that connects an LLM to your own data: it reads documents, builds indexes and search, and can assemble agents on top.
A low-level library for agents modelled as a state graph. It gives you long-running flows, saved progress and pauses for human approval.
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.
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 framework where instead of hand-tuning prompts you describe a program from modules, and the system tunes prompts and examples against a quality metric.
A fast engine for serving language and multimodal models. A vLLM rival, especially strong on large models like DeepSeek.
A modular Microsoft system that builds an entity graph and community summaries from texts, so it can answer questions about a whole corpus rather than one passage.
A free Hugging Face course on agents in four units: fundamentals, the smolagents, LlamaIndex and LangGraph frameworks, agentic RAG and a final benchmark assignment.
OpenAI's lightweight SDK: agents, tools, handoffs between agents and guardrails. Few abstractions, so it is quick to learn.
A tiny Hugging Face library where the agent solves a task by writing its steps as Python code instead of JSON tool calls. Works with many models.
Apple's array framework for its own chips: a NumPy- and PyTorch-like interface that uses the Mac's unified memory. The base for running and training models on a Mac.
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 long-standing ML platform that now covers LLM apps too: tracing, evaluation, a prompt registry and a model gateway. Plugs into most frameworks.
A Python framework that hides the protocol plumbing: a decorated function becomes an MCP tool. The shortest path from idea to a working server.
A curated list on large language models: milestone papers, open models, training and inference frameworks, courses and books. A good reference for a first look at the field.
A framework for assembling LLM apps from modular pipelines with explicit control over retrieval, routing and memory. Strong at RAG and search systems.
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.
Google's code-first agent framework: build agents in Python, run evaluations and deploy. Tuned for Gemini but works with other models too.
An agent framework from the makers of Pydantic: strict types in and out, many models, voice and embeddings. Mistakes surface before you run anything.
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.