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 21, 2026

repositories
224
categories
11
stars in total
11M
new stars in 30 days
+219K

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 30 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+13K in 27 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

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 30 dPython

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+6.5K in 28 dTypeScript

Comfy-Org

ComfyUI

Growing fastest

A node-based builder for diffusion pipelines: wire up image, video and audio generation visually. Runs locally and exposes API endpoints.

148Kstars+5.5K in 29 dPython

Catalog

141 repositories

microsoft

markitdown

Growing fastest

A small Microsoft utility that converts PDF, Word, PowerPoint, Excel and other files into Markdown that is easy to hand to a language model.

197Kstars+5.4K in 29 d15KPythonCommit 14 days ago

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+13K in 27 d23KPythonCommit 5 days ago

Significant-Gravitas

AutoGPT

A platform where you build agents in a visual builder or by describing them in plain words, then run them on a schedule or a trigger. Hosted version plus free self-hosting.

188Kstars+331 in 27 d46KPythonCommit 3 days ago

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 30 d19KGoCommit 1 day ago

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 30 d35KPythonCommit 1 day ago

The classic browser UI for Stable Diffusion: text-to-image, inpainting, upscaling and thousands of community extensions.

165Kstars+242 in 29 d31KPythonCommit 9 months ago

langgenius

dify

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.

162Kstars+2.2K in 29 d26KPythonCommit 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 29 d23KSvelteCommit 2 days ago

langflow-ai

langflow

A visual builder for AI agents and workflows in Python: drag components, test the chain in chat and publish it as an API.

157Kstars+732 in 28 d10KPythonCommit 3 days ago

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 30 d14KPythonCommit 2 days ago

langchain-ai

langchain

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.

150Kstars+1.3K in 28 d25KPythonCommit 4 days ago

Comfy-Org

ComfyUI

Growing fastest

A node-based builder for diffusion pipelines: wire up image, video and audio generation visually. Runs locally and exposes API endpoints.

148Kstars+5.5K in 29 d18KPythonCommit today

Shubhamsaboo

awesome-llm-apps

A large collection of ready-made LLM apps: agents, RAG systems and skills for coding agents. Every template can be run and taken apart piece by piece.

145Kstars+2.4K in 29 d21KPythonCommit 3 days ago

browser-use

browser-use

A library that lets an agent drive a browser: open sites, click, fill in forms. Works with a local browser or a cloud one.

121Kstars+2.7K in 30 d14KPythonCommit 3 days ago

openai

whisper

OpenAI's reference speech-recognition model: transcribes audio in dozens of languages, translates speech and detects the language.

113Kstars+2K in 29 d14KPythonCommit 3 months ago

Code for Sebastian Raschka's book: you build a GPT-like model in PyTorch step by step, then pretrain and finetune it. The best way to see how an LLM works inside.

109Kstars+1.6K in 29 d17KJupyter NotebookCommit 1 day ago

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 2 days 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 30 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 29 d25KPythonCommit 1 day ago

3b1b

manim

An animation engine Grant Sanderson uses to make 3Blue1Brown videos, including the well-known neural network ones. It is not an AI library but a tool for explaining math and ML visually.

97Kstars+1.2K in 29 d7.9KPythonCommit 2 months ago

unclecode

crawl4ai

An open-source Python crawler: it visits pages with a real browser and returns clean Markdown for LLMs. Runs locally, in Docker or as a cloud service.

88Kstars+1.5K in 30 d9.1KPythonCommit 3 days ago

opendatalab

MinerU

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.

84Kstars+1.7K in 29 d6.9KPythonCommit 1 day 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 30 d7.4KPythonCommit 1 day ago

A collection of examples and guides for the OpenAI API: from basic requests to function calling and RAG. Most code is Python.

77Kstars+471 in 29 d13KJupyter NotebookCommit 1 day ago

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 2 days ago

FoundationAgents

MetaGPT

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.

71Kstars+394 in 30 d9.1KPythonCommit 10 months ago

docling-project

docling

An IBM library for document parsing: PDF, Office, HTML and images become one unified structure from which Markdown is easy to get. Supports vision models for hard pages.

71Kstars+1.1K in 27 d5.4KPythonCommit 3 days ago

mem0ai

mem0

A memory layer for agents: it remembers facts about the user across sessions and pulls up the right ones at the right moment, keeping context small.

69Kstars+1.6K in 30 d8.2KPythonCommit 3 days ago

More than 60 PyTorch implementations of research papers with notes next to the code: transformers, optimizers, GANs, reinforcement learning. The website shows code and notes side by side.

68Kstars+185 in 29 d6.8KPythonCommit 19 days ago

RVC-Boss

GPT-SoVITS

Few-shot voice cloning: about a minute of recorded speech is enough to fine-tune a text-to-speech model. Ships a web UI for data prep and training.

65Kstars+1.5K in 27 d6.8KPythonCommit 10 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.