LABSCO SUMMARY

Background operation is the whole point — the machine stays yours while the agent works.

Most desktop automation takes over the pointer, which means you stop working while it runs. Cua Drivers act without stealing cursor or focus, and Linux is documented with explicit limits on raw background input rather than a blanket claim. If what you need is a disposable machine rather than your own, the sandbox side of the same project is the other half.

What it is

The MCP server that ships with Cua Drivers, Cua's background computer-use layer. Agents click, type and verify inside native desktop applications while you keep using the machine: the driver does not take the cursor or the window focus. The same CLI and MCP server work on macOS, Windows and Linux, with X11 and compositor-specific Wayland routes on Linux.

What you get

Native desktop apps driven in the background from Claude Code, Cursor, Codex, OpenClaw or your own client
One toolset across macOS, Windows and Linux, rather than a per-platform automation stack
The wider Cua stack alongside it: agent-ready sandboxes for Linux containers and VMs, macOS, Windows and Android through one API, cloud or local via QEMU
Lume for macOS and Linux VMs on Apple Silicon using Apple's Virtualization.Framework, and Cua-Bench for evaluating computer-use agents on OSWorld, ScreenSpot and Windows Arena

Requirements

The driver install script — curl -fsSL https://cua.ai/driver/install.sh on macOS and Linux, or the PowerShell equivalent on Windows — followed by the post-install steps. The sandbox SDK is a separate pip install cua and needs Python 3.11 or later. MIT licensed; some optional components carry their own licences.

Setup effort

One command — /bin/bash -c "$(curl -fsSL https://cua.ai/driver/install.sh)"

See installation options

USE CASES

01

Having a coding agent verify a change in the real app

Let it open and drive the desktop application while you keep typing — clicks and keystrokes land in the target app, not wherever your cursor is.

02

Automating a desktop workflow that has no API

Script it against the same driver on macOS, Windows or Linux instead of maintaining three platform-specific automations.

03

Running agent work somewhere it cannot break anything

Use a Cua sandbox — an ephemeral Linux, macOS, Windows or Android environment with screenshot, mouse, keyboard and shell — instead of your own desktop.

04

Measuring whether a computer-use agent is actually improving

Run it against the bundled benchmarks and export the trajectories for training.

BEFORE YOU INSTALL

What to know first

Requires

pip on PATH

INSTALLATION

Connect your client

This project publishes no client configuration, so the entry for your client is yours to write.

Server setup

TERMINAL

/bin/bash -c "$(curl -fsSL https://cua.ai/driver/install.sh)"

Cua