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

42 repositories

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 d23KPythonCommit 4 days ago
Growing fastest

Formerly Awesome ChatGPT Prompts: a huge community library of prompts plus an interactive book on prompting. You can deploy your own private copy.

178Kstars+4K in 30 d23KMDXCommit 2 days 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 29 d35KPythonCommit today

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 27 d25KPythonCommit 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 2 days 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+1K in 28 d7.9KPythonCommit 2 months 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

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+1.5K in 30 d5.4KPythonCommit 2 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 2 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+158 in 28 d6.8KPythonCommit 18 days ago

upstash

context7

Feeds fresh, version-specific library docs into the prompt so the model stops inventing outdated APIs. Works as an MCP server or through a CLI with a skill.

65Kstars+1.6K in 29 d3.3KTypeScriptCommit 1 day 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

langchain-ai

langgraph

A low-level library for agents modelled as a state graph. It gives you long-running flows, saved progress and pauses for human approval.

45Kstars+1.4K in 29 d7.8KPythonCommit 1 day ago

facebookresearch

faiss

Meta's classic library for fast similarity search and clustering of vectors. It is not a database but an index engine that many other systems are built on.

42Kstars+623 in 30 d4.7KC++Commit 2 days ago

Google's library for extracting structured data from text with LLMs: each field is tied to a spot in the source, and results can be viewed in an interactive visualization.

39Kstars+302 in 28 d2.8KPythonCommit 10 days ago

huggingface

diffusers

The standard PyTorch library for diffusion models: ready-made pipelines for images, video and audio that run in a few lines.

35Kstars+132 in 27 d7.5KPythonCommit 3 days ago

huggingface

smolagents

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.

30Kstars+440 in 29 d3.2KPythonCommit 2 days ago

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

vercel

ai

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.

28Kstars+602 in 30 d5.6KTypeScriptCommit 3 days ago

Whisper on the CTranslate2 engine: same output, noticeably faster and lighter on memory, including 8-bit mode.

27Kstars+831 in 30 d2.3KPythonCommit 8 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

pgvector

pgvector

A Postgres extension that adds a vector type and nearest-neighbor search. It lets you keep embeddings next to regular data without running a separate database.

24Kstars+300 in 30 d1.4KCCommit 1 day 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

guidance-ai

guidance

A language for controlling generation: you mix text and constraints right in Python, and the model must produce exactly the required format, including schema-bound JSON.

22Kstars+23 in 30 d1.2KJupyter NotebookCommit 6 months 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

karpathy

micrograd

A tiny autograd engine with a small neural net on top and a PyTorch-like API. Very little code, yet it shows exactly how backpropagation works.

19Kstars+1K in 30 d3KJupyter NotebookCommit 4 months ago

andrewyng

aisuite

A unified interface to different generative AI providers: you only change the model string, such as `openai:gpt-4o` to `anthropic:...`, and the rest of the code stays the same.

16Kstars+51 in 30 d1.7KPythonCommit 2 months ago

vibrantlabsai

ragas

A metrics library for evaluating RAG and other LLM apps: it checks how well an answer relies on retrieved sources. Can also generate test sets.

16Kstars+264 in 30 d1.8KPythonCommit 6 days ago

ggml-org

ggml

A small tensor library in plain C/C++ with no dependencies. It underpins llama.cpp and whisper.cpp and runs quantized models on CPU, GPU and in the browser.

16Kstars+600 in 30 d2.1KC++Commit 4 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.