An objective comparison of multiple frameworks that allow us to "transform" our web apps to desktop applications.

Is an experimental backend for Wine that implements NT-style synchronization primitives (Event, Mutex, Semaphore) entirely in userspace, with no kernel drivers or Wine server dependency.

A macOS scripting add-on that minimizes/removes space switching animation durations.

100% private on-device voice models for speech-to-text and meeting transcription on macOS

Official repo for CFG-Zero*

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

A ~9M parameter LLM that talks like a small fish.

AI Browser

Focus on prompting and generating

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Have a natural, spoken conversation with AI!

Bonsai Demo

MLX native implementations of state-of-the-art generative image models

MLX version of z-image model

🧩 Content editing tech stack for the web - BlockSuite is a toolkit for building editors and collaborative applications.

SketchCrapp - Crack your Sketch.app in seconds :) Supports MacOS Big Sur. With respect from 1337 leet xnu crackers original founders: @elijahtsai ✨🧪 & @duraki ✨🧪

The project has now moved to KDE Invent.

God's algorithm for Rubik's Cube in Python. Solve the cube with the smallest possible number of moves.

Official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

A voice assistant that runs completely on your local device.

Multilingual Voice Understanding Model

A tutorial on infinite canvas

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Generate audiobooks from e-books

Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

The open source coding agent.

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms