@Saccc_c: 发现了一个能让 DSH 也具备堪比Codex computer use能力的好工具 直接复制粘贴下面这个命令,给你的DSH等任意Agent装上手和眼睛: Install or upgrade macOS Harness from http…
摘要
macOS Harness 是一个开源工具,允许 AI 代理通过原始 macOS 原语在 Mac 上执行任务,具备类似 Codex computer use 的能力。
查看缓存全文
缓存时间: 2026/08/18 22:39
发现了一个能让 DSH 也具备堪比Codex computer use能力的好工具
直接复制粘贴下面这个命令,给你的DSH等任意Agent装上手和眼睛:
Install or upgrade macOS Harness from https://github.com/browser-use/macos-harness… with uv using Python 3.12. Register the skill printed by macos-harness skill, then run macos-harness doctor. Explain any missing macOS permissions and ask before requesting them. Finally, verify the harness by capturing one already-running app without bringing it to the foreground.
我实际测试了下,用DSH配合v4 flash搜索并打开youtube视频,感觉的确和Codex一样丝滑
browser-use/macos-harness
Source: https://github.com/browser-use/macos-harness
macOS Harness ⌘
The simplest, thinnest harness that gives an LLM complete freedom to complete virtually any task on a Mac.
The agent writes what is missing, mid-task. No framework, no recipes, no rails. One Python process connected directly to macOS, your real browser, and your files.
● agent: wants to do something no helper exists for
│
● sees the app and uses raw macOS primitives
│
● writes the missing logic in ordinary Python
│
✓ task complete no app-specific tool added
Your agent now has a Mac.
Give it to your agent
Paste this into Codex or Claude Code:
Install or upgrade macOS Harness from https://github.com/browser-use/macos-harness with uv using Python 3.12. Register the skill printed by `macos-harness skill`, then run `macos-harness doctor`. Explain any missing macOS permissions and ask before requesting them. Finally, verify the harness by capturing one already-running app without bringing it to the foreground.
That is it. The agent installs the package, teaches itself the workflow, checks permissions, and verifies the connection. Manual setup is available too.
Six primitives. The whole Mac.
macos-harness <<'PY'
frame = mac.see("Spotify")
mac.key("cmd+k", app="Spotify")
mac.type("Alessia Cara", app="Spotify")
mac.click(640, 420, app="Spotify")
item = mac.ax.at(640, 420, app="Spotify")
mac.script('tell application "Spotify" to play')
print(browser.page_info())
print(list(Path.home().iterdir()))
PY
Think in see, key, type, click, ax, and script. browser, Path, and
subprocess are ready in the same Python process.
There are no Spotify tools, Slack tools, or Final Cut tools. The model gets raw primitives and writes the rest.
How it works
one persistent Python process
│
┌──────────────────────┼──────────────────────┐
│ │ │
mac.* browser.* Path / subprocess
│ │ │
┌───────────┼───────────┐ Browser Harness files + shell
│ │ │ │
CGWindow CGEvent AX + Apple CDP
screenshots to PID Events │
│ │ │ real Chrome
└───────────┴───────────┘
│
native + Electron apps
- Captures background app windows without bringing them forward
- Sends keyboard and coordinate input directly to an app PID
- Draws an animated, click-through pointer without moving your real cursor
- Exposes raw Apple Accessibility and Apple Events when vision is not enough
- Uses Browser Harness for the real, logged-in browser
- Keeps ordinary Python and the local filesystem within reach
Permissions and privacy
macos-harness doctor reports the macOS permissions actually needed. The harness
never activates or raises a target app and never moves the physical pointer.
Anonymous telemetry is enabled by default. It records only the CLI command category, success, duration, package version, OS/architecture, and detected agent client. It never records prompts, app names, screenshots, UI text, scripts, paths, or window titles.
macos-harness telemetry disable
Experimental. macOS only. MIT licensed.
相似文章
@Saccc_c: 我用 Codex 对 DeepSeek Harness的GitHub仓库进行了详细分析 发现其大量使用Codex进行辅助开发,也少量的使用了 Claude Code 总结而言,Deepseek 官方都认可了 Codex 和 Claude,…
作者用 Codex 分析了 DeepSeek Harness 的 GitHub 仓库,发现其大量使用 Codex 和少量 Claude Code 进行辅助开发,暗示 DeepSeek 官方认可这些 AI 编码工具。
@XChatScout: https://x.com/XChatScout/status/2056622783761899644
详细教程,介绍如何利用 MacBook、Mac mini、Codex、OpenClaw(龙虾)和 Tailscale 搭建一套个人专属的超级 AI 系统,实现远程协作与自动化任务。
@geekbb: Agent harness 自动化优化工具,接管了 Agent harness 优化的脏活,你给一个基准测试命令和目标仓库,它就自动生成提案、跑评测、记结果、留好的,弃差的,自动改进 agent 的 prompt、配置和源码。 https…
autoharness 是一个自动化代理 harness 优化工具,能基于基准测试命令自动生成提案、运行评估并改进 agent 的 prompt、配置和源码,支持 Codex 和 Claude。
@geekbb: 一个专为 AI 编码设计的 macOS 终端,把工作区管理、分屏和 AI agent 启动流程整合到一起。支持横竖分屏,一键启动 Claude Code、Codex、Gemini CLI 等七个 AI agent,右键选中内容直接提交给 …
kooky 是一个专为 AI 编码设计的 macOS 终端,整合工作区管理、分屏和 AI agent 启动流程,支持一键启动多个 AI agent 和右键提交内容。
@jinglian: 卧槽,Codex 可以使用你的 iPhone! 介绍一下:phone-harness > 像人类一样自动化任何 iOS 应用 > 原生 iPhone 控制 → 无需 API,无需越狱 > 连接一次,随时控制 只需一个提示即可设置。 立即开…
介绍 phone-harness,一个开源工具,通过 macOS 的 iPhone Mirroring 让 LLM(如 Codex)像人类一样自动化任意 iOS 应用,无需 API 或越狱,利用屏幕截图、Vision OCR 和 HID 事件实现视觉与操作。