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
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.
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.
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.
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
Catalog
121 repositories
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 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.
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.
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.
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.
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.
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.
A node-based builder for diffusion pipelines: wire up image, video and audio generation visually. Runs locally and exposes API endpoints.
A collection of system prompts and tool descriptions from popular AI products: Cursor, Devin, Windsurf, Lovable, Manus and others. Useful for studying how pros build them.
OpenAI's lightweight coding agent that runs in the terminal and works on your project's code. Written in Rust.
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.
A free 21-lesson Microsoft course that goes from generative AI basics and prompting to working applications. Each lesson ships with code.
OpenAI's reference speech-recognition model: transcribes audio in dozens of languages, translates speech and detects the language.
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.
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.
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.
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.
A 12-week course on classic machine learning: 26 lessons and 52 quizzes. The foundation that makes modern models easier to understand.
Reference MCP servers from the protocol team: memory, git, filesystem and more. A solid pattern for how a server is built and a ready set to start with.
The open DeepSeek-R1 model, trained with reinforcement learning to reason step by step, plus its smaller distilled versions on Qwen and Llama.
A platform where you assemble a team of AI agents, schedule them and get reports. Works with many models; deploy on Vercel or with Docker.
A three-part LLM roadmap: fundamentals, the LLM Scientist (building models) and the LLM Engineer (building apps). Topics come with Colab notebooks.
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.
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.
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.
A coding agent, a fork of Codex tuned for cheap and open models. It can emulate other agents' harnesses to get the most out of a weaker model.
A ready-made «chat with your documents» app: plug in any model and vector database, upload files and talk to them. Has a desktop version, Docker and agents.
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.
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.
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.










