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.
A Go tool that bridges AI coding assistants like Claude Code and Cursor running on your computer to messaging apps like Slack, Telegram, and WeChat, so you can interact with your coding agent from your phone without a public IP address.
CC-Connect is a bridge that connects AI coding assistants running on your computer to messaging apps on your phone or browser. Tools like Claude Code, Cursor, Gemini CLI, and Codex are programs you run locally to help write, review, and debug code. CC-Connect lets you talk to those tools through platforms you already use, such as Slack, Telegram, Discord, Feishu, DingTalk, LINE, or WeChat Work, so you can interact with your AI coding agent from anywhere without being at your computer.
The core problem it solves is that these AI coding tools normally only work through a terminal or IDE on the machine where they are installed. If you want to check on a long-running coding task or send it a follow-up instruction while you are away from your desk, you have no way in. CC-Connect creates that connection by running a small local service that relays messages between the messaging app and the AI tool. Most supported messaging platforms do not require your machine to have a public IP address, meaning you can use this from a home network without special router configuration.
The project is written in Go and is available both as a downloadable binary and as an npm package, so it can be installed with Node.js tooling if preferred. The README is primarily in English with a Chinese translation also available.
The README is long and includes a large section of sponsor advertisements from companies offering AI API relay services and Claude Code hosting. Beyond the sponsorship content, the README describes the supported messaging platforms and AI tools and provides setup instructions for each combination. A Discord community and Telegram group are linked for support.
The project is released under the MIT license.
Where it fits
- Send instructions to a running Claude Code session from Telegram while away from your desk.
- Monitor a long-running AI coding task from your phone via Discord without needing a public IP address.
- Connect your local Cursor IDE session to a Slack channel so teammates can see AI agent updates.
- Interact with Gemini CLI through WeChat Work or DingTalk from anywhere.