nativ
Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.
它通过手柄控制、地形跟随、速度切换等类游戏移动方式,实现了大型 3D 扫描模型的沉浸式探索,弥补了原生 visionOS 模型查看器的不足。
A little visionOS app for walking around inside large USDZ models (house scans, terrain, etc.) on Apple Vision Pro, with game controller support for movement.
I built this for myself (well, I vibe coded it so if any code is janky please don't yell at me), so it's rough around the edges and not the most straightforward to use, but it should be a fun starting point if you want to explore your own large models in an immersive space.
.usdz file into the Prospector folder in Xcode.modelName at the top of ImmersiveView.swift to your file's name (without the extension).Pair a game controller (e.g. a DualSense or Xbox controller) with your Vision Pro. Movement is relative to the direction you're looking.
| Input | Action |
|---|---|
| Left thumbstick | Move |
| Right thumbstick | Look (yaw) |
| Left / right trigger | Move down / up |
| D-pad up | Reset height to the terrain surface |
| D-pad right | Toggle terrain follow (height snaps to the ground as you move) |
| D-pad left | Toggle speed mode (6× movement) |
You can also pinch your thumb and middle finger together for half a second (either hand) to toggle the model's visibility.
The environment skybox is the Meadow 2 HDRI from Poly Haven (CC0).
A visionOS app to preview large scale models in real life (like housing plans!)
根据分类、Topic 和编程语言匹配的相似项目。
Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.
A macOS command-line tool that uses Apple's on-device speech APIs to transcribe prerecorded audio into plain text, JSON, JSONL, SRT, or WebVTT.