guo6x/dsh-pilot 预览 preview

guo6x/dsh-pilot

给你的 DSH 智能体装上双手:通过聊天驱动真实浏览器(基于 CDP 的 Edge/Chrome)——支持参考驱动的点击、独立会话浏览器,以及实时驾驶舱面板。零运行时依赖,无需 API 密钥。

Project Overview项目介绍

dsh-pilot is a native plugin built exclusively for DeepSeek Harness (DSH) that enables the DSH agent to control a locally installed Chrome or Edge browser via the Chrome DevTools Protocol. It exposes a set of tools that let the agent open pages, interact with elements by reference to pre-numbered structured DOM snapshots, fill forms by human-readable labels, take screenshots, evaluate JavaScript, and navigate through pages. Installation is straightforward: users can run the one-liner dsh plugin --profile web add github:guo6x/dsh-pilot from their terminal, then restart the DSH web process and refresh the UI to activate it.

After installation, a small airplane icon will appear in the bottom sidebar of the DSH web UI. Clicking this icon opens a draggable cockpit overlay that displays a live refreshed screenshot of the current browser page, the current URL, a log of recent actions, and controls to start or stop the browser instance. Each DSH agent session gets its own isolated browser instance with a separate user data profile, so parallel browsing sessions do not interfere with each other, and users can switch between sessions or pin the cockpit to follow the most recent activity automatically.

dsh-pilot requires Node.js 22 or newer and a local installation of Chrome or Edge, and has no other runtime dependencies. It does not require any API keys, sends no telemetry data to third parties, and all processing happens locally on the user's machine. Known limitations include one tab per session, no headed browser mode, and it is released under the permissive MIT open source license, so users can modify or redistribute it freely per license terms.

dsh-pilot 是专为 DeepSeek Harness(DSH)开发的原生浏览器自动化插件,允许DSH代理直接驱动本地已安装的Chrome或Edge浏览器,通过Chrome DevTools协议(CDP)实现网页打开、元素点击、文本输入、表单填写、截图、JS执行等操作。它生成带编号的结构化DOM元素快照,代理通过引用定位目标,无需猜测CSS选择器,操作精度远高于常规方案。用户仅需执行一条命令即可完成安装,重启DSH web服务后即可启用。

插件提供了一个可拖动的驾驶舱面板,悬浮在DSH的Web界面上,实时展示当前浏览器的页面截图、地址、操作日志,支持多会话切换,用户可以随时暂停代理操作,手动接管浏览器。它支持每个代理会话独立分配浏览器实例,多会话并行不会互相干扰,适合让代理完成网页搜索、表单填写、信息抓取、站点测试等需要浏览器交互的任务。

该插件无需额外依赖,仅要求Node.js版本≥22,使用本地已有的Chrome或Edge,不需要额外API密钥或第三方服务,所有数据都在本地处理。目前已知限制为每个会话仅支持单个标签页,仅支持无头模式运行。它采用MIT开源许可证,完全免费使用,无内置遥测或第三方网络调用。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示
  • 22 stars - an early-stage project星标 22,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add github:guo6x/dsh-pilot

把 guo6x/dsh-pilot 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

🛩️ dsh-pilot — give your DSH agent hands

Awesome DSH Plugin dsh-recommend dsh score ci 中文说明 · DeepSeek Harness plugin

Drive a real browser from the DeepSeek Harness chat: the agent opens pages, reads them as structured text with a numbered element list, clicks and types by ref (no CSS guessing), presses keys, navigates back/reload, waits, evaluates JS, and takes screenshots — while you watch a live draggable cockpit panel in the Web GUI and can take over at any time.

  • 🚀 One command install — dsh plugin --profile web add github:guo6x/dsh-pilot
  • ⚡ Zero runtime dependencies — talks CDP over the native Node ≥ 22 WebSocket, uses the Edge/Chrome already on your machine
  • 🔑 No API key — nothing leaves your machine; no vision model required
  • 📖 Text-first by design — the agent reads DOM snapshots (title/URL/text/links + numbered elements), so text-only models browse without burning vision tokens
  • 🎯 Ref-driven interaction — every click/type targets a snapshot ref, not a guessed selector; stale refs fail loudly with a hint
  • 📝 Human-named forms — fill several fields by label, aria-label, placeholder, name, or id, and upload files by ref
  • 🧭 Full navigation set — back, reload, and wait tools for real browsing flows, with page-settling waits built in
  • 👀 Human in the loop — live screenshot, URL bar, action log, and a session switcher in the cockpit; you see everything the agent does
  • 🧩 Per-session isolation — every agent session gets its own browser instance; parallel sessions never fight over one page

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-desktop-windowos 下一个 Next dsh-with-pencil →