DeepSeek Harness Plugin
🔍 中文

dsh-wechat-bridge

💬 Sessions & Messages ⭐ 7 stars DSH Plugin

A transport plugin that puts your DeepSeek Harness agents on WeChat using Tencent's official iLink bot channel. It needs no runtime dependencies or OpenClaw — just a QR-code login — and keeps one persistent agent session per friend.

Plugin facts

GitHub stars⭐ 7
LicenseMIT
Primary languageJavaScript
Last push2026-08-16T15:22:19Z
Maintainergtaifu
Added to this directory2026-08-15

Screenshots

About this plugin

DeepSeek Harness (dsh) transport plugin: chat with your agents on WeChat via official Tencent iLink bot API — zero runtime deps, no OpenClaw, QR-code login, one friend = one persistent agent session.

Install this DSH plugin

Copy the command below and run it in your DeepSeek Harness terminal.

dsh plugin add github:gtaifu/dsh-wechat-bridge

⚠️ Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →

About this plugin: dsh-wechat-bridge

What is dsh-wechat-bridge?

dsh-wechat-bridge is a sessions & messages plugin maintained by gtaifu. A transport plugin that puts your DeepSeek Harness agents on WeChat using Tencent's official iLink bot channel. It needs no runtime dependencies or OpenClaw — just a QR-code login — and keeps one persistent agent session per friend.

How do I install dsh-wechat-bridge?

Run dsh plugin add github:gtaifu/dsh-wechat-bridge in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:gtaifu/dsh-wechat-bridge#commit.

Is dsh-wechat-bridge free?

dsh-wechat-bridge is a community open-source project released under the MIT license. You can inspect its source and install it for free.

dsh-router-standard

★ Featured ⭐ 299

Sessions & Messages

A task-aware reasoning-mode router for DeepSeek Harness. Each task is placed on one continuous react-to-spec axis, the router picks from three measured behavior bands before the first model request, and persona plus first-turn tool injection are supported with agent-visible tuning.

View plugin → yjh051108 GitHub profile image yjh051108