Nativ

Nativ

Local AI, native to your Mac.

Chat, serve, monitor, and connect MLX models from one macOS app.

Nativ is a native macOS workspace for running AI models locally on Apple silicon. It bundles an `mlx-vlm` (opens in a new tab) server, finds compatible models in your Hugging Face cache (honoring HF_HUB_CACHE and HF_HOME), and wraps the whole experience in a polished SwiftUI app.

Use Nativ as a private chat app, a model manager, a performance dashboard, or an OpenAI- and Anthropic-compatible local inference server for the tools you already use.

Documentation

Full feature and contributor documentation lives in [`Docs/`](Docs/README.md) — start there for [Chat](Docs/features/chat.md), [Models](Docs/features/models.md), [Voice](Docs/features/voice.md), [Scheduled tasks](Docs/features/routines.md), [Integrations](Docs/features/integrations.md), and the [Developer](Docs/features/developer.md) reference, plus guides for [extensions](Docs/extending/extensions.md), [kits](Docs/extending/kits.md), and the [MCP catalog](Docs/extending/mcp-catalog.md).

What Nativ can do

Inference runs on your Mac after a model has been downloaded. Model downloads and first-time build dependencies still require network access.

How it works

NativServerKit owns the embedded Python distribution and server lifecycle. The app adds model discovery, chat, analytics, configuration, integrations, logs, menu bar controls, and software updates around that runtime.

Requirements

To run the app:

• A Mac with Apple silicon.
• macOS 26 or newer.
• Enough unified memory for the model you choose.
• Optional: a Hugging Face token (set in the app or via HF_TOKEN) to download gated models.

To build from source, you will also need:

• Xcode with the macOS 26 SDK.
• The Xcode Metal Toolchain for the embedded terminal (xcodebuild -downloadComponent MetalToolchain).
• `xcodegen` (opens in a new tab).
• Python 3.
• Network access to GitHub Releases and PyPI while the embedded Python bundle is first assembled or refreshed.

Get started

Use Nativ as a local API server

By default, the app exposes its server at http://127.0.0.1:8080. You can change the host and port in the Developer page, which also lists every available endpoint and lets you copy URLs directly.

For example, with a model selected:

If you enabled a server API key, also send it as a Bearer token:

The server includes:

• OpenAI-compatible /v1/chat/completions, /v1/responses, /v1/models, image, and audio routes.
• Anthropic-compatible /v1/messages and token-counting routes.