Culeot/dsh-weixin-bridge

Plugin插件 ⭐ 2 MIT Notifications & Remote通知与远程

Chat with your local DeepSeek Harness (DSH) from WeChat. Send a message on your phone; DSH runs it as a real task on your computer (tools, files, commands); the reply comes back to WeChat.

catalog descriptioncatalog 简介 / catalog description:test

Project Overview项目介绍

dsh-weixin-bridge is a native plugin built exclusively for DeepSeek Harness (DSH) that lets you remotely trigger DSH agent tasks from WeChat. When you send a message to the linked bot on your WeChat mobile app, your local DSH instance running on your computer will execute the task as an agent, then send the final reply back to your WeChat. You do not need a public IP address, install any extra software on your phone, or use a desktop WeChat client to use this tool. All you need to do is scan a QR code once to log in via WeChat's official iLink channel.

The bridge works by long-polling the WeChat iLink API for incoming messages, then runs the requested task via dsh --profile headless on your local machine, then sends the DSH-generated response back to WeChat. It keeps the last 20 turns of conversation context to maintain a continuous dialog, so you don't have to re-explain context for every new task. While your task is running, you will get immediate "processing" progress updates, so you never have to wait in silence for a reply. Only your logged-in WeChat account can trigger tasks, which adds a layer of security.

To install the tool, you first need Node.js version 20 or higher and a globally installed DSH instance accessible via the dsh command line. If your DSH is installed in a non-standard location, you can set the DSH_BIN environment variable to point to DSH's bin.js before starting the bridge. After installing Node.js and DSH, you install the bridge globally via npm, run the login script to scan a QR code with WeChat, then start the bridge service. You can customize core settings like working directory, task timeout, poll interval, and maximum history length directly in the bridge code. The tool is open source under the MIT license and no API key is required.

这是一个专门为DeepSeek Harness(DSH)开发的原生插件,支持你通过微信远程调用本地计算机上运行的DSH。你只需在手机微信给绑定的机器人发送任务消息,本地DSH就会执行对应的代理任务,处理完成后把结果返回你的微信。不需要公网IP,也不需要额外在手机上安装软件,仅通过微信官方iLink通道扫码登录即可使用。

典型工作流程是,桥接程序通过长轮询微信官方iLink通道获取新消息,然后调用DSH的无头模式执行任务,最后把DSH生成的回复发回微信。它会保留最近20轮对话上下文,维持连续的对话状态,任务执行过程中还会实时返回进度提示,不会出现静默等待。只有扫码登录的微信账号能触发任务,有效保障使用安全。

安装使用需要先准备Node.js 20以上版本和全局安装的DSH,之后全局安装本桥接工具,完成微信扫码登录就可以启动桥接服务。你可以自定义代理任务的工作目录、单任务超时时间、轮询间隔和保留的最大对话轮数,适配不同使用需求。本工具遵循MIT许可开源,不需要额外申请API密钥,完全免费使用。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 项注意
  • Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
  • No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单:可能只是打了 dsh-plugin 话题,安装方式要现场确认
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:Culeot/dsh-weixin-bridge

把 Culeot/dsh-weixin-bridge 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-weixin-bridge

Chat with your local DeepSeek Harness (DSH) from WeChat. Send a message on your phone; DSH runs it as a real task on your computer (tools, files, commands); the reply comes back to WeChat.

No public IP needed, no desktop WeChat, nothing to install on your phone — it talks through the official WeChat iLink channel (the same API WeChat's own bots use) with a QR-code login.

No API key needed. Replies are produced by your local DSH in agent mode — it reuses the model already configured in DSH. You never paste a DeepSeek/OpenAI key into this tool.

How it works

WeChat message
  → bridge polls the official iLink channel (long-polling)
  → task runs through `dsh --profile headless "message"` (a DSH dialog / agent on your PC)
  → the agent's reply is sent back to WeChat
  • Context kept: the bridge remembers the last 20 turns, so the bot keeps one continuous dialog instead of forgetting everything each message.
  • Progress feedback: you immediately get "⏳ processing…" and periodic updates while a task runs — no silent waiting.
  • Only you: only the WeChat account that scanned the QR code can trigger tasks.

Installation guide (from zero)

  1. Install Node.js >= 20 — https://nodejs.org
  2. Install DeepSeek Harness (global, so its bin.js lives under Node's node_modules):
    npm install -g @deepseek-ai/dsh
    
    Then verify the one-shot mode works:
    dsh --profile headless "hi"
    # should print a reply; if it errors, check the headless profile / your DSH install
    

    If DSH is installed elsewhere, set DSH_BIN to its dsh/lib/bin.js path before starting the bridge.

  3. Install this tool:
    npm install -g dsh-weixin-bridge
    # or clone https://github.com/Culeot/dsh-weixin-bridge and npm install
    
  4. Log in with WeChat (one time):
    node login.js
    # a QR code appears → scan with WeChat → confirm → the bot is linked
    
  5. Start the bridge:
    node bridge.js
    # logs "bridge started, waiting for WeChat messages"
    
  6. Test: in WeChat, message the bot — "hi", or "list what's in C:\ai项目". You should get "⏳ processing…" then the reply.

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-wallpaper-bridge 下一个 Next dsh-desktop →