npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

dsh-weixin-bridge

v0.1.2

Published

Chat with your local DeepSeek Harness (DSH) from WeChat: messages enter a DSH dialog (agent executes locally), replies go back to WeChat. Official WeChat iLink channel, no public IP, no desktop WeChat needed.

Readme

dsh-weixin-bridge(微信远程助手)

用手机微信直接跟电脑上的 DeepSeek Harness(DSH) 对话。你发一条消息,DSH 就在电脑上把它当成真任务执行(工具、文件、命令),回复再发回微信。

不需要公网 IP、不需要电脑登录微信、手机端零安装——走微信官方 iLink 通道(微信自家机器人用的那套 API),扫码即连。

不需要 API Key:回复由你本地的 DSH 在 agent 模式下生成——直接复用 DSH 里已配置好的模型。这个工具不碰任何 DeepSeek/OpenAI 密钥。

原理

微信发消息
  → 桥进程轮询微信官方 iLink 通道(长轮询)
  → 消息交给 dsh --profile headless "消息"(电脑上的 DSH 对话框/agent 执行)
  → agent 的回复发回微信
  • 持续上下文:桥记住最近 20 轮对话,机器人保持同一个对话框,不会每句都失忆
  • 进度反馈:发消息立刻回"⏳ 正在处理…",任务跑得久会定时更新进度,不会干等
  • 只认你:只有扫码登录的那个微信号能触发任务

安装引导(从零开始)

  1. 装 Node.js >= 20 — https://nodejs.org
  2. 装 DeepSeek Harness(全局安装,这样它的 bin.js 在 Node 的 node_modules 下):
    npm install -g @deepseek-ai/dsh
    然后验证一次性模式能用:
    dsh --profile headless "你好"
    # 能回复就 OK;报错的话检查 headless profile 或 DSH 安装

    如果 DSH 装在别处,启动桥之前设 DSH_BIN 指向它的 dsh/lib/bin.js

  3. 装本工具:
    npm install -g dsh-weixin-bridge
    # 或 clone https://github.com/Culeot/dsh-weixin-bridge 后 npm install
  4. 微信扫码登录(一次性):
    node login.js
    # 出现二维码 → 手机微信扫 → 确认 → 机器人上线
  5. 启动桥:
    node bridge.js
    # 日志显示"bridge started, waiting for WeChat messages"
  6. 测试:微信里给 bot 发消息——"你好",或"看看 C:\ai项目 里有什么"。先收到"⏳ 正在处理…",然后收到回复。

配置

bridge.js 顶部常量:

| 常量 | 默认 | 含义 | |---|---|---| | AGENT_CWD | C:/ai项目 | agent 任务的工作目录(改成你自己的) | | AGENT_TIMEOUT | 300s | 单任务超时 | | POLL_INTERVAL | 5s | 微信轮询间隔 | | MAX_HISTORY | 20 | 保留的对话轮数(上下文) |

登录后 bot 凭据存在 account.json(已 gitignore)。

开机自启(可选)

注册表加一项:

HKCU\Software\Microsoft\Windows\CurrentVersion\Run
WeixinBridge = powershell -WindowStyle Hidden -Command "Start-Process node -ArgumentList 'C:\路径\bridge.js' -WindowStyle Hidden"

常见问题

  • bot 不回:看项目目录的 bridge.log,多数是 dsh --profile headless 执行失败——先手动跑那条命令
  • 提示"找不到 DSH / DSH not found":DSH 不在当前 Node 可找到的位置——全局装一次,或设 DSH_BIN
  • 二维码过期:重新 node login.js
  • 回复慢:headless 每条消息都启动一个全新 DSH 进程(冷启动要几秒),进度提示会告诉你它还在干活
  • 模型配置:agent 用 DSH 里配的模型(在 DSH 设置里配,比如 deepseek-v4-flash),这里不用填 key

安全说明

  • 只有扫码的微信号能触发任务,别人的消息不理会
  • 任务可以在电脑上执行命令,注意保管好 token:account.jsonbridge.log 已 gitignore
  • 走的是微信官方 iLink API,不涉及任何第三方微信协议

文件

| 文件 | 用途 | |---|---| | bridge.js | 桥主体:轮询 → headless 执行 → 回复(带上下文与进度) | | login.js | 扫码登录,保存 bot 账号 |

License

MIT