The open source coding agent.

Stable Diffusion in pure C/C++

Homomorphic Encryption library and applications in Swift

Native Apple Silicon LLM server on MLX with chat UI, menu bar app, and CLI. OpenAI & Ollama compatible. Supports Apple Foundation Models.

MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.

Swift API for MLX

Run LLMs with MLX

MLX: An array framework for Apple silicon

Model Context Protocol Servers

LM Studio TypeScript SDK

LM Studio in your terminal

LLM inference in C/C++

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

Free, local, open-source AI app builder ✨ v0 / lovable / Bolt alternative 🌟 Star if you like it!

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon.

Qwen-Image text to image lora trainer

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

Enjoy the magic of Diffusion models!

The "classic" version of the Forge WebUI

Straightforward, type-safe argument parsing for Swift

Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-spee…

Examples in the MLX framework

Apple MLX engine for LM Studio

The official Python SDK for Model Context Protocol servers and clients

SoTA open-source TTS

Pure C++ implementation of several models for real-time chatting on your computer (CPU)

A collection of MCP servers.

Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻