trycua / cua

trycua / cua

Build, benchmark, and deploy agents that use computers. 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.

构建、基准测试并部署能够使用计算机的智能体。选择你的路径:正在构建自己的智能体?从 Cua 开始 · 想给编程智能体配备一台电脑?使用 Cua Drivers · 需要评估或训练模型?使用 Cua Bench · 需要 macOS 虚拟机?使用 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.

Cua Drivers - macOS 和 Windows 上的后台计算机操作(Linux 版本预发布)

在后台驱动原生桌面应用程序。智能体可以在不抢占鼠标光标或焦点的情况下进行点击、输入和验证。在 macOS 和 Windows 上,你可以通过 Claude Code、Cursor、Codex、OpenClaw 及自定义客户端使用相同的 CLI 和 MCP 服务器。Linux 支持目前作为预发布后端提供,平台测试仍在进行中。

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

然后将其作为 MCP 服务器接入 Claude Code,你的智能体即可在后台驱动桌面: 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.

完整的工具参考、架构说明以及可选的智能体技能包请见:libs/cua-driver/README.md


Cua - Agent-Ready Sandboxes for Any OS

Build agents that see screens, click buttons, and complete tasks autonomously. One API for any VM or container image — cloud or local.

Cua - 适用于任何操作系统的智能体就绪沙箱

构建能够观察屏幕、点击按钮并自主完成任务的智能体。无论云端还是本地,任何虚拟机或容器镜像只需一套 API。

pip install cua # Requires Python 3.11 or later
from cua import Sandbox, Image

# Same API regardless of OS or runtime
async with Sandbox.ephemeral(Image.linux()) as sb: # or .macos() .windows() .android()
    result = await sb.shell.run("echo hello")
    screenshot = await sb.screenshot()
    await sb.mouse.click(100, 200)
    await sb.keyboard.type("Hello from Cua!")
    await sb.mobile.gesture((100, 500), (100, 200)) # multi-touch gestures

Cua-Bench - Benchmarks & RL Environments

Evaluate computer-use agents on OSWorld, ScreenSpot, Windows Arena, and custom tasks. Export trajectories for training.

Cua-Bench - 基准测试与强化学习环境

在 OSWorld、ScreenSpot、Windows Arena 和自定义任务上评估计算机操作智能体。导出轨迹以供训练使用。

# Clone, install, and create base image
git clone https://github.com/trycua/cua && cd cua/cua-bench
uv tool install -e . && cb image create linux-docker

# Run benchmark with agent
cb run dataset datasets/cua-bench-basic --agent cua-agent --max-parallel 4

Lume - macOS Virtualization

Create and manage macOS/Linux VMs with near-native performance on Apple Silicon using Apple’s Virtualization.Framework.

Lume - macOS 虚拟化

利用 Apple 的 Virtualization.Framework,在 Apple Silicon 芯片上以近乎原生的性能创建和管理 macOS/Linux 虚拟机。

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

# Pull & start a macOS VM
lume run macos-sequoia-vanilla:latest

Packages (软件包)

PackageDescription
cua-driverBackground computer-use agent for macOS, Windows, and Linux
cua-agentAI agent framework for computer-use tasks
cua-sandboxSDK for creating and controlling sandboxes
cua-computer-serverDriver for UI interactions and code execution in sandboxes
cua-benchBenchmarks and RL environments for computer-use
lumemacOS/Linux VM management on Apple Silicon
lumierDocker-compatible interface for Lume VMs
软件包描述
cua-driver用于 macOS、Windows 和 Linux 的后台计算机操作智能体
cua-agent用于计算机操作任务的 AI 智能体框架
cua-sandbox用于创建和控制沙箱的 SDK
cua-computer-server用于沙箱内 UI 交互和代码执行的驱动程序
cua-bench用于计算机操作的基准测试和强化学习环境
lumeApple Silicon 上的 macOS/Linux 虚拟机管理
lumierLume 虚拟机的 Docker 兼容接口

Resources (资源)

  • Documentation — Guides, examples, and API reference

  • Blog — Tutorials, updates, and research

  • Discord — Community support and discussions

  • GitHub Issues — Bug reports and feature requests

  • 文档 — 指南、示例和 API 参考

  • 博客 — 教程、更新和研究

  • Discord — 社区支持与讨论

  • GitHub Issues — 错误报告和功能请求

Contributing (贡献)

We welcome contributions! See our Contributing Guidelines for details.

我们欢迎贡献!详情请参阅我们的贡献指南。

License (许可)

MIT License — see LICENSE for details. Third-party components have their own licenses: Kasm (MIT), OmniParser (CC-BY-4.0). Optional cua-agent[omni] includes ultralytics (AGPL-3.0).

MIT 许可 — 详情请参阅 LICENSE 文件。第三方组件拥有各自的许可:Kasm (MIT), OmniParser (CC-BY-4.0)。可选的 cua-agent[omni] 包含 ultralytics (AGPL-3.0)。

Trademarks (商标)

Apple, macOS, Ubuntu, Canonical, and Microsoft are trademarks of their respective owners. This project is not affiliated with or endorsed by these companies.

Apple、macOS、Ubuntu、Canonical 和 Microsoft 是其各自所有者的商标。本项目与这些公司无关联,也未得到其认可。

Thank you to all our GitHub Sponsors! 感谢所有 GitHub 赞助者!