Top APPLE-SILI GitHub Repositories & Tools (2026)

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

A local inference engine for Apple silicon, built around the model.

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

Run Omarchy on MacOS without any setup.

Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API

Run Windows games on Apple Silicon — free, open source, with an open compatibility database that tells you what actually works.

Every display control macOS hides, in one menu bar app: sharp HiDPI/Retina scaling (no more blurry or tiny text), DDC brightness and volume, Extra Brightness past 100%, presets, virtual displays. Free and open source, a no-cost alternative to BetterDisplay and Lunar.

A diagnostic performance logging utility for macOS: logs CPU, memory, GPU, network, and battery from the menu bar to help detect and diagnose performance issues. Free, open source, no telemetry.

Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)

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

Widelands is a free, open source real-time strategy game with singleplayer campaigns and a multiplayer mode. The game was inspired by Settlers II™ (© Bluebyte) but has significantly more variety and depth to it.

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

Free, open-source fan control for Apple Silicon Macs (M1, M2, M3, M4, M5). Menu bar app + CLI. Alternative to Macs Fan Control, TG Pro, AlDente.

Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.

Let idle local LLMs sleep and get your Mac's memory back. A native macOS menu bar app to turn Ollama on and off and auto-free idle model RAM. Free and open source.

👋 Your face is the password. Face unlock for your Mac's lock screen, plus App Lock for chosen apps. 100% on-device, built with Swift and Core ML.

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

Run Stable Diffusion on Mac natively

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

chad: a coding agent for your macbook pro