chenhg5/cc-connect

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.

What it solves

cc-connect allows users to control AI agents running on their local machines from any instant messaging platform. This removes the need to be physically at the computer where the agent is running, enabling remote code review, research, automation, and data analysis via a mobile phone, tablet, or any device with a chat app.

How it works

It acts as a bridge (connector) between local AI agents and various messaging platforms. By integrating with these platforms, it relays commands from the chat app to the local agent and sends the agent's responses back to the user.

Who it’s for

Developers and power users who run local AI agents (such as Kimi CLI or Cursor CLI) and want to interact with them remotely through chat interfaces.

Highlights

  • Broad Platform Support: Connects local agents to Feishu/Lark, DingTalk, Telegram, Slack, Discord, and WeCom.
  • Remote Execution: Allows users to ask agents to inspect or modify code, troubleshoot issues, and run commands from anywhere.
  • Agent Integration: Specifically supports tools like Kimi CLI and Cursor CLI.

Related

  • Project
    formulahendry/wechat-acp

    A bridge that connects WeChat direct messages to ACP-compatible AI agents, allowing users to interact with local AI CLI tools via WeChat.

  • Project
    xvirobotics/metabot

    A self-hosted personal agent workbench that bridges AI coding engines like Codex and Kimi Code to messaging apps like Telegram and Slack for mobile-friendly AI development.

  • Project
    sgaofen/cli-in-wechat

    A bridge service that lets you run and control AI programming CLI tools like Claude Code and Gemini CLI remotely via WeChat using the official ClawBot API.

  • Project
    sandbox-quantum/switch

    Switch is an open‑source framework that connects LLM‑based or custom AI agents to existing chat platforms (Slack, Teams, Discord, Telegram, Mattermost). It provides a central server (Switch Core) with PostgreSQL‑backed rooms, bridges for each messaging app, and an Agent Bridge that lets any agent speak a simple HTTP + SSE protocol. A desktop client (Switch Console) lets you define agents, create rooms, set roles/instructions, and run the server locally or remotely. The goal is to let humans and AI agents collaborate in the tools they already use, without replacing the chat stack.

  • Project
    deepcoldy/botmux

    botmux is a self‑contained binary that lets you start and control AI‑coding CLI agents (like Claude‑Code, Codex, Gemini, etc.) from Feishu/Lark messages. Each chat message spawns an isolated CLI process; its output streams back as live‑updating cards, and you can interact via a web terminal, hand‑off sessions, schedule tasks, or run multiple bots in the same group. Installation is a one‑line script (or npm) and works on Linux/macOS (WSL2 for Windows).