Moxin Applications
AI Crafted in Pure Rust
Native Desktop Intelligence — No Python Required
The Way of the Artisan
Like the ancient seal carvers who shaped meaning into stone with precision and intent, we craft AI tools with the same deliberate mastery.
Pure Rust
Every line of code, from UI to inference, written in Rust. No Python runtime, no garbage collection pauses, no compromise.
Metal Accelerated
Direct GPU access through Apple Metal. Models run at native speed on Apple Silicon, with zero abstraction overhead.
Locally Native
Your data never leaves your machine. Full AI capabilities running natively on your desktop, private by design.
Tools of the Craft
Native AI applications built with the Moxin stack — each one a testament to what's possible when performance meets purpose.
A native desktop application that runs LLMs, generates images, clones voices, and transcribes speech — all locally on Apple Silicon. No cloud, no Python, no waiting.
▶ Overview playing — click a feature to explore
View on GitHubLive translation with real-time bilingual subtitles at its core. Clone any voice from seconds of audio and generate natural speech across Chinese, English, Japanese, and Korean.
▶ Overview playing — click a feature to explore
View on GitHubForged in Rust
A vertically integrated stack from metal to pixel. Every component chosen for performance, every abstraction earned.
Rust
Systems language powering every layer
Memory safety without garbage collection
Makepad
GPU-accelerated native UI framework
Pure Rust, cross-platform rendering
OminiX MLX
Apple Silicon inference engine
Metal GPU acceleration for ML models
Dora
Dataflow orchestration framework
Connecting AI pipelines seamlessly
Open Source
Every application in the Moxin ecosystem is open source under Apache 2.0. Inspect the code, contribute improvements, or build your own tools on our stack.