open-computer-use

iFuryStMIT活跃维护

开源桌面自动化 Agent 框架,通过辅助功能接口操控电脑完成跨平台 GUI 任务,可作为 Codex Computer Use 的自托管替代方案。

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

v1.1.4发布于 2026-11-07 06:57 UTC2,910star +26 / 7 天270fork同步于 2026-11-10 11:42 UTC

怎么上手

由 README 提炼,执行前请确认
npm i -g open-computer-use
open-computer-use install-codex-mcp
硬件要求按 README 说明

README 未说明显存或 GPU 要求;macOS 运行时需 macOS 14.0 或以上,Windows 与 Linux 无需额外授权步骤。

下载:源码 zip·GitHub Releases(安装包)本站不镜像安装包

项目说明

由 README 自动翻译提炼

把 Computer Use 封装成 MCP 服务的开源工具,让任意 AI Agent 跨平台操控桌面

开源桌面自动化 Agent 框架,通过辅助功能接口操控电脑完成跨平台 GUI 任务,可作为 Codex Computer Use 的自托管替代方案。

核心能力

  • 以 MCP 服务形式暴露 Computer Use 能力,任意 MCP 客户端可接入
  • 基于 Accessibility 实现非侵入式桌面操控,支持 macOS、Linux、Windows
  • 提供 install-codex-mcp 等命令一键写入各 Agent 配置
  • 支持 call 子命令单次调用工具或按序列复用 element_index 状态
  • macOS 支持 Locked Use,锁屏后临时解锁并加全屏防护继续执行

容易踩的坑

macOS 首次运行需手动授予辅助功能(Accessibility)和屏幕录制权限,Windows/Linux 无此步骤;macOS 运行时要求 14.0 及以上版本;接入 Agent 前需先执行对应 install-*-mcp 命令或手动写 MCP 配置,否则客户端看不到该服务。

内容由模型根据 README 生成,可能不完整或不准确,以官方文档为准。看原文 README

最近发版

5 个版本v1.1.4
  1. v1.1.4最新正式版2026-11-07 · 2026-11-07 06:57 UTC

    What's Changed

    • Fix Locked Use cleanup after idle timeout and Guardian reconnection so completed sessions can release protection and allow the next task. #158
    • Preserve visible controls and action buttons when large accessibility trees reach their node budget on macOS, Windows, and Linux. #145
    • Verify actual values after setting controls across platforms, including when action read-back is disabled; preserve whitespace and support clearing fields. #111

    Full Changelog: https://github.com/iFurySt/open-computer-use/compare/v1.1.3...v1.1.4

  2. v1.1.32026-11-01 · 2026-11-01 03:06 UTC
    查看更新说明

    What's Changed

    • Improve macOS automation with more accurate coordinate clicks, focused-sheet snapshots, live-focus text replacement, faster accessibility reads, and more reliable permission guidance.
    • Add macOS text selection and optional accessibility-tree or screenshot collection across platforms; improve Windows scrolling and scaled-display input, and reduce Linux observation overhead. Virtual displays now require explicit opt-in.
    • Preserve notarization tickets for installable Locked Use components and refresh packaged artifacts after notarization.

    Full Changelog: https://github.com/iFurySt/open-computer-use/compare/v1.1.2...v1.1.3

  3. reference-bundlesOfficial Computer Use Reference Bundlespre-release2026-10-19 · 2026-10-19 15:40 UTC
    查看更新说明

    Official Computer Use Reference Bundles

    This archival pre-release preserves historical official computer-use plugin bundles for reverse engineering, version comparison, and reproducible research. These files are reference inputs and are not part of the Open Computer Use build or installation process.

    Downloads

    FileSize (bytes)SHA-256
    1.0.750.zip134584957afe231e98ddb3b95030c8c56bb178a0217e98fcbb08abf9e1b467fd7ead5b9d
    1.0.755.zip13467875cfabe3f41bfec1ea1d5f99ca2f5424eac98487e9474a099394c372d5df7a6460

    Download both ZIP files and the attached SHA256SUMS into the same directory, then verify them:

    shasum -a 256 -c SHA256SUMS
    

    The versioned files use the fixed reference-bundles tag rather than the software release's latest URL. They are uploaded Release assets, so downloading them does not use Git LFS bandwidth. Existing filenames and the archival tag should be retained; future bundle versions should use new filenames.

    See the reference bundle documentation for download commands and maintenance details. Historical commits may still contain LFS pointers; this migration does not rewrite Git history or restore an already consumed monthly LFS allowance.

  4. v1.1.22026-10-17 · 2026-10-17 07:23 UTC
    查看更新说明

    What's Changed

    • Kept the macOS software cursor aligned with moving windows during motion, click feedback, and idle waits.
    • Fixed Linux action read-back configuration so batch operations can skip automatic snapshots while preserving the last observed element indexes.
    • Updated package and installation links to the renamed open-computer-use repository while preserving existing package names, CLI aliases, and app identity.

    Full Changelog: https://github.com/iFurySt/open-computer-use/compare/v1.1.1...v1.1.2

  5. v1.1.12026-10-15 · 2026-10-15 14:29 UTC
    查看更新说明

    What's Changed

    • Improved macOS Locked Use authorization and installation, with a plug-in load check before activation and clearer component version diagnostics.
    • Reduced idle polling and repeated signature checks, and fixed a socket cleanup issue that could disconnect the automation client.
    • Fixed removal and replacement of older Locked Use components while preserving native password authentication.

    Full Changelog: https://github.com/iFurySt/open-codex-computer-use/compare/v1.1.0...v1.1.1

用户点评

登录用户的真实使用记录,可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译

    open-computer-use

    English 简体中文 Release Ask DeepWiki

    [!TIP] Interested in Browser Use? Check out open-browser-use.


    open-computer-use is an open-source Computer Use service wrapped as MCP. Any AI agent or MCP client can use it to run Computer Use on macOS, Linux, and Windows.

    This project was inspired by OpenAI's Codex Computer Use. It showed that non-intrusive CUA can be built on top of Accessibility, so I decided to build an open-source version.

    I started this repo with my harness template, a template for quickly spinning up AI-first projects. It has been one of our most useful workflows lately, especially for nearly 100% AI-generated projects. I also wrote a post about the methodology behind it.

    Demos

    Codex App and Codex CLI

    Open Computer Use custom demo cover

    open-computer-use used as Computer Use in Codex App and Codex CLI, matching the official experience.

    Gemini CLI

    https://github.com/user-attachments/assets/eacb3b15-f939-46c7-b3b3-6f876977a58d

    Gemini CLI connects to open-computer-use through MCP and runs full Computer Use actions.

    Linux

    https://github.com/user-attachments/assets/e036b1c8-2200-4896-abd4-19225915cf66

    open-computer-use running on Linux.

    Locked Use

    Locked Use is now supported on macOS. OCU temporarily unlocks your Mac after it has been locked so the agent can continue working, with protective services such as a full-screen shield in place during use.

    Open Computer Use Locked Use screen

    See the Locked Use guide for setup, installed components, and permissions

    Quick Start

    npm i -g open-computer-use
    

    The npm package also exposes ocu as the short CLI alias.

    [!IMPORTANT] The macOS runtime requires macOS 14.0 or later.

    On macOS, run it once and grant Accessibility and Screen Recording. Windows and Linux do not need this step.

    open-computer-use
    # or
    ocu
    

    Before using it, install it into your agent:

    # Install into Codex by writing to ~/.codex/config.toml
    open-computer-use install-codex-mcp
    ocu install-codex-mcp
    

    Or add it to your own client manually:

    {
      "mcpServers": {
        "open-computer-use": {
          "command": "open-computer-use",
          "args": ["mcp"]
        }
      }
    }
    

    Skill

    Install the skill directly:

    # Install for Codex
    npx skills add iFurySt/open-computer-use -g -a codex --skill open-computer-use -y
    npx skills ls -g -a codex | rg 'open-computer-use'
    

    Install for Claude Code:

    npx skills add iFurySt/open-computer-use -g -a claude-code --skill open-computer-use -y
    

    Update an existing global install, including the Codex install created above:

    npx skills update open-computer-use -g -y
    

    You can also manually download and install the open-computer-use skill.

    More

    Besides the MCP JSON config above, you can also use the built-in commands:

    # Install into Codex by writing to ~/.codex/config.toml
    open-computer-use install-codex-mcp
    
    # Install as a Codex plugin, mainly for Codex App
    open-computer-use install-codex-plugin
    
    # Install into Claude Code by writing to ~/.claude.json
    open-computer-use install-claude-mcp
    
    # Install into Gemini CLI for the current project by writing to ./.gemini/settings.json
    open-computer-use install-gemini-mcp
    
    # Install into Gemini CLI user config instead
    open-computer-use install-gemini-mcp --scope user
    
    # Install into opencode by writing to ~/.config/opencode/opencode.json (or the active config file)
    open-computer-use install-opencode-mcp
    
    # Call a single Computer Use tool and print the MCP-style JSON result
    open-computer-use call list_apps
    ocu call list_apps
    open-computer-use call get_app_state --args '{"app":"TextEdit"}'
    
    # Run a sequence in one process so element_index state can be reused
    # Sequence runs sleep 1s between successful operations by default
    open-computer-use call --calls '[{"tool":"get_app_state","args":{"app":"TextEdit"}},{"tool":"press_key","args":{"app":"TextEdit","key":"Return"}}]'
    open-computer-use call --calls-file examples/textedit-overlay-seq.json --sleep 0.5
    
    # Check permissions; onboarding only opens when something is missing
    open-computer-use doctor
    
    # macOS: query permission JSON without opening onboarding
    ocu doctor --json
    
    # Show help
    open-computer-use -h
    ocu -h
    

    Global Configuration

    ocu supports global configuration starting with version 1.0.0 to accommodate different workflows and use cases. The default configuration file is ~/.config/ocu/config.json. You can edit the file directly or use the ocu config subcommands. See the configuration guide for details.

    Star History

    License

    MIT