# Hanzo Desktop — Hanzo AI

> Native desktop app for macOS, Windows, and Linux. Run local models, orchestrate AI agents, and manage cloud workspaces.

Native Desktop Client

# Hanzo Desktop

Build agents on your own machine

[Download](https://docs.hanzo.ai/docs/apps/desktop)[GitHub](https://github.com/hanzoai)

Desktop — Hanzo

[CLI](https://hanzo.ai/cli)[Playground](https://hanzo.ai/playground)[Desktop](https://hanzo.ai/desktop)[API Keys](https://hanzo.ai/cloud/api-keys)

- Add rate limiting to the payments API.
- Read 14 files. The limiter belongs in the gateway, not the handler — one place, every route.
- Wrote gateway/limit.go and a test at 100 req/min per key. Tests pass.

[Open in the console](https://hanzo.ai/home)

Example project. Every name in it is one you would give your own.

Paste and ship

Paste this into any agent. It reads the skill manifest and calls Desktop from there.

Agent promptCopy

```
Read https://hanzo.ai/skill.md and use Hanzo Desktop in my project.
```

## What you can build in it

Free and open source. Download it, and the first agent is a few minutes of clicking.

01

### Nothing to scaffold

An agent is made in the window: give it a job, some tools, and a model. There is no project to create first and no file to check in before it exists.

02

### Local model or cloud model, per agent

Point one agent at a model running on your machine and another at one on Hanzo Cloud. It is a setting on the agent, not a decision about the whole install.

03

### They work together

Agents share context and hand steps to each other, so a job that needs several of them is one workflow instead of you copying between three chat windows.

04

### It works with the network off

With a local model pinned, an agent keeps running when the connection goes. Nothing has to be uploaded for it to do its job.

05

### Your keys stay on your machine

Keys and the data an agent touches stay local. An agent that has to pay for something spends from a key you hold, on hardware you own.

06

### MCP is how it reaches your tools

Agents speak the Model Context Protocol, so a tool you have already connected elsewhere works here without a second integration written for this app.

## Available everywhere you work

Native installers for macOS (Apple Silicon + Intel), Windows, and Linux.

macOSarm64 + intel

Windowsx64 + arm64

Linuxdeb + rpm + AppImage

## Download it and build one

Pick a model, describe the job, hand it the tools. If the model is a local one, the whole thing runs without an account.

[View on GitHub](https://github.com/hanzoai)

Related capabilities

[Desktop docs →](https://docs.hanzo.ai/docs/apps/desktop)

[CLI](https://hanzo.ai/cli)[Playground](https://hanzo.ai/playground)[API Keys](https://hanzo.ai/cloud/api-keys)

## Get Desktop

Desktop client

License: Apache-2.0[hanzoai](https://github.com/hanzoai)

[Deploy to Cloud](https://platform.hanzo.ai/deploy)[Self-host](https://docs.hanzo.ai/docs/apps/desktop)
