dsh-computer-use:DeepSeek Harness 桌面操作插件

dsh-computer-use(v0.5.6)是 orangeofcarl0-sys 维护的 DeepSeek Harness 客户端插件,通过 cua-driver 实现观察→定位→自动升级投递→验证的桌面自动化。默认折叠仅暴露 computer_do 与 screen_observe,展开后提供 21 个工具;后台优先三级投递、窗口本地像素坐标、UIA 验证与子 agent 委派。安装依赖 Node≥22.18.0、DSH≥0.1.5-rc.2,使用 install.sh 链接 profile。设计为无感自治:零审批,密码框为唯一硬拒绝。

Read More
dsh-computer-use:Windows 桌面自动化插件

DSH 插件 `dsh-computer-use` 将 Codex 的原生 Windows 计算机使用能力接入 DSH,通过 stdio 协议驱动本机程序。它利用 UI Automation 和 SendInput 实现界面识别与操作,提供应用枚举、输入注入、剪贴板、截图及窗口故障自愈等核心功能。插件要求安装 Codex 桌面版,应用操作需通过免审批白名单或 DSH 弹窗授权。使用 6 个工具(如 `computer_use_act`、`computer_use_wait`)进行状态获取、动作执行和等待。注意 Win10 截图较慢,浏览器和终端受策略限制。

Read More
dsh-computer-use: Vision, Accessibility, and Interaction Tools for DeepSeek Harness

The DeepSeek Harness (DSH) plugin `dsh-computer-use` provides models with a complete computer operation toolkit, including 18 `computer_*` tools. It supports accessibility observation, visual recognition, and native input operations on Windows (UIA/MSAA/Narrator), macOS, and Linux. It also offers background capture, multi-monitor support, and an independent accessibility loop. After installation, models can operate desktop applications through accessibility interfaces or the visual pathway, even without native image capabilities. Windows native capabilities are currently the primary focus of validation, while contract tests for macOS and Linux have also been completed.

Read More
Introduction to the DeepSeek Harness Plugin: dsh-computer-use

`dsh-computer-use` is a plugin developed by DeepSeek Harness (DSH) for the Linux X11 environment to address the complexity of operating-system interaction for AI agents. It uses lightweight Python scripts to invoke `libX11` and `libXtst`, enabling features such as screen capture, mouse movement, clicking, dragging, scrolling, and keyboard input. The plugin does not depend on Node.js or accessibility frameworks; once installed, it can directly control the desktop, with `danger-full-access` sandbox mode enabled by default. Note that it supports Linux X11 only and provides full desktop control.

Read More
dsh-computer-use: General-Purpose Computer Use Capabilities of DeepSeek Harness

`dsh-computer-use` is a plugin for DeepSeek Harness that provides agents with a unified computer operation interface. It wraps the underlying drivers through `ctx.computerUse`, supports multiple backends such as Playwright and the Windows native assistant, and integrates accessibility and visual perception modes. The plugin provides security mechanisms, Cookie Bridge support, and depends on several DSH base plugins. Its configuration is flexible and can be modified in real time via the GUI, but there are platform limitations and configuration isolation issues caused by App-Bound Encryption. When using it, be careful to import only required data and configure a domain whitelist.

Read More
DeepSeek Harness Plugin: dsh-computer-use

`dsh-computer-use` is a native Windows desktop automation plugin for DeepSeek Harness (DSH), designed to provide a lightweight control solution. It directly calls the DSH Cordis tool registry and relies on `user32.dll` to perform operations such as taking screenshots, clicking, dragging, and typing, without relying on the MCP protocol, with the native approval service enabled by default to ensure security. The plugin supports sending screenshots to external vision models for analysis. Installation requires specifying the DSH configuration file and restarting; it is currently supported only on Windows, and it is recommended to use `/permission workspace-write` in conversations to prevent operations from being denied.

Read More
dsh-computer-use: Teaching DeepSeek Harness to Operate Computers

dsh-computer-use is an MIT-licensed DSH plugin maintained by JasonWei04 that encapsulates the entire pipeline of "screenshot/recording → Xiaomi MIMO visual analysis → real keyboard/mouse/window/program control → autonomous loop" into a tool, enabling the pure text models of DeepSeek Harness to operate real Windows desktops to complete GUI tasks. The workflow is fixed into three steps: observe, analyze, and execute: `computer_screenshot` for screenshots (delegable to MIMO for static analysis), `computer_record` for recording frame extraction (to observe dynamic processes), `computer_action` for single-step operations (supporting clicks, drags, input, launching programs, etc.), while `computer_use` then autonomously loops...

Read More
dsh-computer-use: Foreground-Safe Native macOS Control Capabilities for DSH Agent

dsh-computer-use is a DSH plugin maintained by Anionex, providing Accessibility-first computer control capabilities for macOS 14+. It is centered around fresh observation, expired state rejection, and scoped permissions. By default, it does not move the system cursor or perform global pointer injection, instead dispatching fallback input to target processes and windows. The article introduces the plugin's positioning, core functions, npm installation commands, Skill loading methods, and typical workflows, while also explaining applicable scenarios, permission requirements, and security considerations.

Read More