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

38 repositories

ollama

ollama

The easiest way to run an open model on your own machine: one command downloads and starts it, plus a local REST API and libraries for Python and JavaScript.

188Kstars+3.3K in 29 d19KGoCommit today

huggingface

transformers

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.

169Kstars+1.3K in 29 d35KPythonCommit today

open-webui

open-webui

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.

159Kstars+2.5K in 28 d23KSvelteCommit 1 day ago

ggml-org

llama.cpp

Growing fastest

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.

136Kstars+3.7K in 29 d26KC++Commit today

pytorch

pytorch

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.

106Kstars+674 in 30 d31KPythonCommit 1 day ago

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

vllm-project

vllm

An engine for fast model serving on GPUs: frugal with memory and handles many requests at once. The default pick when a model has to run as a service.

97Kstars+2K in 28 d25KPythonCommit today

deepseek-ai

DeepSeek-R1

The open DeepSeek-R1 model, trained with reinforcement learning to reason step by step, plus its smaller distilled versions on Qwen and Llama.

92Kstars+107 in 29 d12KCommit 1 year ago

unslothai

unsloth

A tool for running and fine-tuning models while saving memory: there is a desktop app, a web UI and a library. Fine-tuning works on a modest GPU.

80Kstars+1.4K in 29 d7.4KPythonCommit today

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.

76Kstars+473 in 30 d9.4KPythonCommit 1 day ago

karpathy

nanoGPT

A minimal, readable GPT implementation in PyTorch by Andrej Karpathy: training from scratch and fine-tuning in a few hundred lines. The best way to see how a language model works.

65Kstars+920 in 29 d11KPythonCommit 1 year ago

keras-team

keras

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.

64Kstars+52 in 30 d20KPythonCommit 2 days ago

BerriAI

litellm

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.

64Kstars+1.7K in 29 d13KPythonCommit today

karpathy

nanochat

The whole path from zero to your own ChatGPT-like chat in one repo: tokenizer, pretraining, fine-tuning and UI. Designed to train for roughly a hundred dollars.

61Kstars+1.9K in 29 d8.5KPythonCommit 2 months ago

mudler

LocalAI

A local replacement for cloud APIs: an OpenAI-compatible server that runs text, voice and image models on any hardware, no GPU required.

50Kstars+620 in 30 d4.6KGoCommit 2 days ago

exo-explore

exo

Joins several devices into one AI cluster so you can run models too big for a single machine's memory. Devices discover each other automatically; there is a dashboard and an API.

48Kstars+490 in 30 d3.6KPythonCommit 13 days ago

janhq

jan

A desktop ChatGPT alternative that works fully offline: download a model and chat, with nothing leaving your machine.

46Kstars+779 in 30 d3.2KRustCommit 2 days ago

lm-sys

FastChat

An open platform for training, serving and evaluating chat models. It produced Vicuna and runs Chatbot Arena, where people blind-compare model answers.

40Kstars4.8KPythonCommit 7 months ago

sgl-project

sglang

A fast engine for serving language and multimodal models. A vLLM rival, especially strong on large models like DeepSeek.

39Kstars+1.5K in 30 d11KPythonCommit 1 day ago

karpathy

llm.c

GPT-2 training in plain C and CUDA, no PyTorch. Shows what happens under the hood while a model learns.

32Kstars+305 in 28 d3.8KCudaCommit 1 year ago

ml-explore

mlx

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.

29Kstars+313 in 28 d2.4KC++Commit today

fastai

fastai

A layer on top of PyTorch that reduces training a network to a few lines. It comes with the well-known free fast.ai course, which makes it a handy place to start.

28Kstars+45 in 30 d7.6KJupyter NotebookCommit 2 months ago

QwenLM

Qwen3

The open Qwen3 model family from Alibaba, from small to large, with reasoning modes. The README collects run examples for Transformers, llama.cpp and Ollama.

28Kstars+67 in 30 d2.1KPythonCommit 11 months ago

mozilla-ai

llamafile

Packs a model and its engine into one executable file: download, make it executable, run. Works across operating systems with no install.

27Kstars+198 in 28 d1.7KC++Commit 11 days ago

A fast, memory-efficient implementation of attention that large-model training and inference on GPUs lean on. The result is exact, with no approximation.

25Kstars+136 in 30 d3.2KPythonCommit 2 days ago

huggingface

datasets

A library for working with datasets: one line loads thousands of ready-made sets from the Hub or your local files and processes them fast. It can stream data without a full download.

22Kstars+78 in 30 d3.7KPythonCommit 3 days ago

huggingface

peft

A parameter-efficient fine-tuning library: LoRA and related methods train only a small fraction of the weights. Large models fine-tune on consumer hardware.

22Kstars+85 in 30 d2.7KPythonCommit 2 days ago

openai

gpt-oss

Two open OpenAI models, gpt-oss-120b and gpt-oss-20b, plus reference run implementations including Metal for Mac. A rare case of OpenAI releasing weights.

21Kstars+67 in 30 d2.2KPythonCommit 22 days ago

huggingface

trl

Hugging Face's library for post-training models: SFT, DPO, GRPO and reward-model training. The base for shaping model behavior after pretraining.

20Kstars+204 in 30 d3.2KPythonCommit 1 day ago

state-spaces

mamba

An alternative to the transformer: a state space model whose runtime grows linearly with text length. A good fit for long sequences.

19Kstars+53 in 28 d1.8KPythonCommit 12 days 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.