Stars
Libraries and models for next-gen UI
A curated list of medical LLMs, multimodal systems, datasets, benchmarks, and more. 🏥
Model export recipes, Python primitives, and Swift runtime utilities for on-device AI
A playful experience where you drag and drop virtual T-shirts onto a model to instantly change their look.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Ableton-Claude-Bridge gives Claude Desktop full read/write access to any Ableton Live 12 session. It runs as an invisible Control Surface — no Max for Live, no devices on any track.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
GUI for a Vocal Remover that uses Deep Neural Networks.
A free, open source, and extensible speech-to-text application that works completely offline.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
The open-source AI voice studio. Clone, dictate, create.
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…
A WebGL viewer for UMAP or TSNE-clustered images
An experimental webgl gallery that can visualize tens of thousands of film posters as a voronoi diagram
Run any LLM locally on iOS or MacOS. Powered by llama.cpp
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.
Magenta RealTime 2: An Open-Weights Live Music Model
ElevenLabs Conversational AI Swift SDK
A powerful AI coding agent. Built for the terminal.
Marquee or "scrolling text" effect in SwiftUI
yet another Arc-as-four-knobs-in-Ableton-Live M4L patch
A TTS model capable of generating ultra-realistic dialogue in one pass.
A SwiftUI Chat UI framework with fully customizable message cells and a built-in media picker
real time face swap and one-click video deepfake with only a single image