cua

trycua/cua

Infrastructure for training and evaluating AI agents to control desktop environments.

19k
Stars
1.3k
Forks
464
Open issues
75
Watchers
HTML MITLast pushed Jul 7, 2026

Overview

trycua/cua is an open-source project providing sandboxed environments, SDKs, and benchmarks to develop, test, and deploy AI agents on various operating systems including macOS, Linux, and Windows.

Categories

Tags

Similar tools

Install

git clone https://github.com/trycua/cua

README

Build, benchmark, and deploy agents that use computers

cua.ai Discord Twitter Documentation
trycua%2Fcua | Trendshift

Choose Your Path

Building your own agent? Start with Cua · Giving a coding agent a computer? Cua Drivers · Evaluating or training models? Cua Bench · Need macOS VMs? Lume


Cua Drivers - Background computer-use on macOS and Windows, with Linux pre-release

Drive native desktop apps in the background. Agents click, type, and verify without stealing the cursor or focus. Use the same CLI and MCP server on macOS and Windows from Claude Code, Cursor, Codex, OpenClaw, and custom clients. Linux support is available as a pre-release backend while platform testing is still in progress.

macOS / Linux

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.sh)"

Windows (PowerShell)

irm https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.ps1 | iex

Then wire it into Claude Code as an MCP server and your agent can drive the desktop in the background:

claude mcp add --transport stdio cua-driver -- cua-driver mcp

Full tool reference, architecture notes, and the optional agent skill pack live here: libs/cua-driver/README.md.


Cua - Agent-Ready Sandboxes for Any OS

Build agents that see screens, click buttons, and comp