The AI movement's repository database

AI repositories catalog

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 November 20, 2026

repositories
224
categories
11
stars in total
11M
new stars in 30 days
+221K

Last 30 days

Growing fastest

The most new stars over the last 30 days.

Full growth ranking
Growing fastest

A skills set and methodology for coding agents: clarify the task, plan, write tests, then code. The agent works with more discipline.

322Kstars+18K in 29 dShell

anthropics

skills

Growing fastest

Anthropic's official collection of Agent Skills: folders with instructions and scripts that Claude loads for a task. A good reference for writing your own.

197Kstars+14K in 30 dPython

firecrawl

firecrawl

Growing fastest

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.

203Kstars+9.3K in 30 dTypeScript

anomalyco

opencode

Growing fastest

An open coding agent for the terminal with a desktop app. It is not tied to one provider: plug in whichever models you have.

228Kstars+8.6K in 30 dTypeScript

github

spec-kit

Growing fastest

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.

151Kstars+8.2K in 29 dPython

openai

codex

Growing fastest

OpenAI's lightweight coding agent that runs in the terminal and works on your project's code. Written in Rust.

136Kstars+5.4K in 29 dRust

Catalog

15 repositories

deepseek-ai

DeepSeek-V3

Repository of the large open DeepSeek-V3 mixture-of-experts model: description, benchmark results and run instructions. It showed an open model can stand next to closed ones.

105Kstars+303 in 29 d17KPythonCommit 1 year ago

huggingface

agents-course

A free Hugging Face course on agents in four units: fundamentals, the smolagents, LlamaIndex and LangGraph frameworks, agentic RAG and a final benchmark assignment.

35Kstars+1.3K in 30 d2.5KMDXCommit 3 days ago

trycua

cua

Tooling for computer-use agents: drivers for several OSes, virtual machines and benchmarks for training and evaluation.

32Kstars+1.6K in 28 d2.4KRustCommit 4 days ago

SWE-agent

SWE-agent

A research agent from Princeton and Stanford: it takes a GitHub issue and tries to fix it. It set the bar on SWE-bench; the authors now recommend mini-swe-agent.

21Kstars+220 in 29 d2.3KPythonCommit 3 days ago

openai

evals

OpenAI's framework for evaluating models plus a registry of ready-made benchmarks. A historically important project that shows how eval templates are structured.

20Kstars+143 in 30 d3.1KPythonCommit 7 months ago

windmill-labs

windmill

A developer platform that turns scripts into webhooks, workflows and UIs. A fast job engine and an open alternative to Retool and Temporal.

19Kstars+354 in 27 d1.2KRustCommit 3 days ago

The standard toolkit for running models through hundreds of academic benchmarks. Many open model leaderboards are built on it.

14Kstars+204 in 30 d3.8KPythonCommit 16 days ago

SWE-bench

SWE-bench

The main benchmark for coding agents: a model must fix real issues from GitHub projects, and the patch is verified with tests in containers.

6.2Kstars+148 in 30 d1.1KPythonCommit 2 months ago

AgentOps-AI

agentops

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.

6Kstars+60 in 30 d665PythonCommit 5 months ago

fchollet

ARC-AGI

A famous abstract-reasoning test: 800 puzzles on coloured grids where you infer the rule from a few examples. Easy for people, long out of reach for models. The repo holds the data and a page for solving tasks by hand.

4.9Kstars+4 in 30 d726JavaScriptCommit 1 year ago

meta-llama

PurpleLlama

Meta's generative AI safety project: the Llama Guard and Prompt Guard filter models, the Code Shield scanner and the CyberSec Eval test suites. It pairs defense with attack-based testing.

4.5Kstars+39 in 28 d790PythonCommit 7 days ago

UKGovernmentBEIS

inspect_ai

A model-evaluation framework from the UK AI Security Institute: tool use, multi-turn dialog, model-graded scoring and over 200 ready-made evals.

3.3Kstars+222 in 30 d943PythonCommit 2 days ago

EleutherAI

pythia

A suite of eight models of different sizes trained on identical data, with 154 saved checkpoints each. It exists to study how a model learns and when knowledge appears in it.

3Kstars+21 in 28 d231Jupyter NotebookCommit 1 year ago

harbor-framework

terminal-bench-1

A benchmark of hard terminal tasks: a set of assignments and a runner where the agent acts as an admin or developer. Has a leaderboard.

2.6Kstars+17 in 30 d567PythonCommit 4 months ago

ethz-spylab

agentdojo

A dynamic environment for evaluating attacks and defenses against LLM agents. It runs an agent on user tasks and checks whether a malicious instruction gets through.

1.1Kstars+105 in 30 d289PythonCommit 6 months ago

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.