Code you can understand and maintain—with AI by your side

Bidirectional, stateful control of Logic Pro from AI assistants. 8 dispatcher tools + 7 resources across 5 native macOS channels.

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

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

🍺 Alcoholless: lightweight security sandbox for Homebrew, AI agents, etc. on macOS

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

The spec of leaderless log protocol used in Ursa

Specification of the ARA Audio Random Access API

Toolkit to analyze and reverse-engineer Logic Pro project files (.logicx).

The JUCE cross-platform C++ framework, augmented with support for the Celemony ARA API

Umbrella installer for all ARA SDK submodules

Command-line program to download videos from YouTube.com and other video sites

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Gradle plugin to automate uploading JetBrains IDE plugins to a private repository and maintaining the plugin entry in updatePlugins.xml

Decompiler from Java bytecode to Java, used in IntelliJ IDEA.

High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts stru…

ACE-Step: A Step Towards Music Generation Foundation Model

A repository for sharing agent capabilities and expertise related to TLA+.

Tools for creating AC7 rhythm files for Casio keyboards (especially CT-X keyboards)

HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

ComfyUI Custom Node for HeartMuLa AI Music Generation and Transcript Text

Examples in the MLX framework

Run LLMs with MLX

MLX: An array framework for Apple silicon

Ongoing research training transformer models at scale

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

FlashAttention (Metal Port)

Inference Llama 2 in one file of pure C

Minimalist ML framework for Rust

A Pure Rust based LLM, VLM, VLA, TTS, OCR Inference Engine, powering by Candle & Rust. Alternate to your llama.cpp but much more simpler and cleaner..