xcisxc29/dsh-wechat

WeChat channel for DeepSeek Harness

What it solves

This plugin allows you to control your DeepSeek Harness (DSH) desktop agent remotely via WeChat. It eliminates the need for a public IP address or complex networking, enabling you to interact with your computer's AI agent from your phone even while the PC is locked.

How it works

Once installed as a plugin in the DSH desktop app, you link your WeChat account by scanning a QR code. The plugin acts as a bridge, forwarding your WeChat messages to the DSH agent and sending the agent's responses, files, and status updates back to your phone. It supports text, voice, photos, and files in both directions, and allows you to manage multiple DSH sessions using simple commands.

Who it’s for

It is for users of the DeepSeek Harness desktop application who want to monitor or control their AI agents while away from their workstations.

Highlights

  • Remote Control: Manage DSH sessions, switch models, and cancel tasks directly from WeChat.
  • Full Media Support: Send and receive files, photos, and voice notes; voice notes can be transcribed to text if the silk-wasm plugin is installed.
  • Proactive Notifications: The agent can send updates to your phone, such as notifying you when a long-running task is complete.
  • Interactive Approvals: If an agent requires permission or a choice, the prompt is sent to your phone for you to answer.
  • Secure Connection: Uses Tencent's official iLink gateway, cryptographically binding the bot to your specific WeChat account without requiring a public-facing server.

Related

  • Project
    spences10/mcp-omnisearch

    An MCP server that provides unified access to multiple web search, AI research, and web scraping providers like Tavily, Brave, and Firecrawl through a single interface.

  • Project
    antoinersx/clawhost

    An open-source cloud hosting platform that enables one-click deployment and management of dedicated VPS instances for AI agent runtimes like OpenClaw and Hermes.

  • Project
    BugTraceAI/BugTraceAI

    BugTraceAI is an open‑source, self‑hosted suite for AI‑augmented web and API pentesting. It consists of four interoperable components—CLI (terminal UI + REST/MCP engine), WEB dashboard, API‑only service, and a Launcher installer—plus model checkpoints on HuggingFace and a vulnerable demo app (BugStore). The AI agents plan and prioritize scans, call deterministic security tools, and produce evidence‑rich reports. Installable via a one‑liner script, it supports multiple LLM providers (OpenRouter, Anthropic, Z.ai, Bedrock, Ollama) and is Apache‑2.0 licensed.

  • Project
    DMontgomery40/deepseek-mcp-server

    DeepSeek MCP Server is a Node.js bridge that lets MCP‑compatible tools talk to DeepSeek’s V4.1 Flash and V4 Pro models. It supports chat (including image inputs), the Responses API, fill‑in‑the‑middle completions, model discovery, balance checks, and a full Files API for reusable images. Run it via stdio or as a local HTTP endpoint, providing only your DeepSeek API key.