metal

bendlang/bend

Bend 2 pairs dependent-type proofs with CPU/GPU-level speed — Bend 2 is a language meant to let AI write code while humans verify it via mechanical proofs instead of trial-and-error. It claims C-like single-core speed, GPU parallelism with no manual threading, and a proof checker that outperforms assistants like Lean or Agda by orders of magnitude. Aimed at developers who want verifiable AI-generated code.

Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh

gfx-rs/wgpu

The native Rust implementation powering WebGPU in browsers — wgpu implements the WebGPU standard as a native Rust library, running on Vulkan, Metal, D3D12, OpenGL, and WebGL2/WebGPU on wasm. It already powers WebGPU support in Firefox, Servo, and Deno, making it a solid pick for Rust devs building cross-platform graphics or games.

A cross-platform, safe, pure-Rust graphics API.

tracel-ai/burn

A Rust deep learning framework that merges training and inference code — Burn runs the same Rust tensor code for training and production, avoiding brittle ONNX export steps. It JIT-compiles tensor ops with kernel fusion for PyTorch-like flexibility without the speed hit, and now offers under-5-second recompiles for fast research iteration.

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

ly05010419/MacNativeGames

Play your own Tears of the Kingdom and Breath of the Wild natively on Apple silicon Mac, iPhone and iPad. Not an emulator: the game's ARM64 code runs directly, NVN rebuilt on Metal. Bring your own game.

jhaizhou-ops/d2r-mobile

Open-source compatibility layer for Diablo II: Resurrected with the Reign of the Warlock expansion. Runs your own Switch copy natively on iPhone, iPad, Mac, Android and HarmonyOS — full touch controls, 60 fps, new endgame modes. Bring your own game files. 开源的《暗黑破坏神 II：狱火重生》术士君临 iOS / macOS / 安卓 / 鸿蒙兼容层

kksimp/Mac.apk

Android apps on Apple Silicon Macs without emulation — Mac.apk runs Android apps as native macOS processes on Apple Silicon—no emulator, VM, or Linux layer underneath. Apps get real Dock icons, resizable windows, GPU rendering, and dark mode support. It's alpha software, useful for Mac users curious about running Android apps directly, with a compatibility list tracking which apps work.

Mac.apk: Run Android apps natively on Apple Silicon Macs

trymirai/uzu

A Rust inference engine built for on-device Metal deployment — Uzu is a Rust-based inference engine for AI models, designed to run directly on-device (iOS, macOS, Mac Catalyst) via Metal for zero-latency, private inference. It ships with Python, TypeScript, and Swift bindings, making it useful for app developers who want LLM or TTS inference without server round-trips.

A high-performance inference engine for AI models

youssofal/MTPLX

Native MTP speculative decoding speeds up local LLMs on Apple Silicon — MTPLX runs Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on Macs using the models' own multi-token prediction heads for exact, batched speculative decoding. It reports roughly 2x decode speed over plain decoding, with a 27B model fitting on 16 GB Macs, via an OpenAI/Anthropic-compatible local server for tools like OpenCode.

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

gauthierpiarrette/highball

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

StayLameBro/backburner

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

nyosegawa/speech.cpp

A whisper.cpp-style toolkit covering TTS, ASR and VAD in one binary — Built on ggml like whisper.cpp, speech.cpp bundles text-to-speech (Qwen3-TTS, Irodori-TTS), speech recognition (Qwen3-ASR, ReazonSpeech, parakeet) and Silero VAD behind one C API and CLI. It runs on CPU, Metal or Vulkan, offers live mic transcription, and serves an OpenAI-compatible audio API, useful for building local voice assistants without cloud dependencies.

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.