Directory

Run open large language models locally with a simple CLI and API — pull a model and start chatting or building.

Hugging Face's library of pretrained models for text, vision, and audio — the standard toolkit for transformer models.

Framework for building applications and agents powered by large language models.

C/C++ library for running LLM inference locally on CPUs and GPUs.

Terminal-based coding agent from OpenAI that reads, edits, and runs code in your local repository.

Inference and serving engine for running large language models.

AI agent platform that writes code, runs shell commands, and browses the web to complete software engineering tasks.

Library for faster fine-tuning and training of large language models with lower memory use.

Multi-agent framework that simulates a software company's roles to turn one-line requirements into code.

Autonomous coding agent for VS Code that can create and edit files, run terminal commands, and use a browser.

Terminal coding agent that lets open models such as DeepSeek, Kimi, and Qwen read, write, and run code.

Memory layer that gives AI agents persistent, personalized recall across sessions.

Desktop and Docker app for chatting with documents and running local LLM-based agents.

Framework for orchestrating role-based, collaborative multi-agent workflows, built independent of LangChain.

Inference code for Meta's Llama family of open large language models.

Extensible AI agent that can install, execute, edit, and test code locally with any LLM backend.

Python framework for connecting LLMs to external data via indexing, retrieval, and document agents.

Open-weights release of xAI's 314B-parameter Grok-1 large language model, with JAX example code.

AI pair programming in your terminal; edits files in your local git repo and commits as it goes.

A self-hostable chat interface supporting multiple AI models and providers with multi-user auth.