在跨操作系统的桌面沙箱中运行计算机使用代理，使用 CUA

Launch computer-use agents in Linux, macOS, Windows, or Android sandboxes and drive full desktop tasks through screenshots, mouse, keyboard, and shell controls.

Prerequisites

Python 3.11+ for the SDK or Node.js for cuabot, plus local QEMU or CUA cloud access depending on runtime choice.

Installation

Use the upstream install or setup path that matches your environment:
- pip install cua
- uv tool install -e . && cb image create linux-docker

Requirements and caveats from upstream:
- python
- # Requires Python 3.11 or later
- | lumier | Docker-compatible interface for Lume VMs |

Basic usage or getting-started notes:
- result = await sb.shell.run("echo hello")
- cd cua-bench
- # Run benchmark with agent

• Source: https://github.com/1991513ccie-png/skills
• Extracted from upstream docs: https://raw.githubusercontent.com/trycua/cua/HEAD/README.md

Documentation

• https://cua.ai