formulahendry/wechat-acp

Bridge WeChat chat messages to any ACP-compatible AI agent (Claude, Codex, Copilot, Qwen, Gemini, OpenCode, OpenClaw, Hermes, Kiro, Kimi, Pi and more)

What it solves

wechat-acp is a bridge that allows users to interact with ACP-compatible AI agents (like Copilot CLI, Claude Code, or Gemini) directly through WeChat direct messages. It removes the need to use a terminal or a dedicated AI app by routing WeChat messages to a local AI agent and sending the agent's responses back to the user.

How it works

The tool logs in via the WeChat iLink bot API and polls for incoming 1:1 messages. When a message arrives, it forwards the content to a configured ACP agent running locally (via stdio) and manages a dedicated session for each WeChat user. It handles various data types, converting agent outputs—such as images, audio, and files—into native WeChat messages. It also provides a buffering mode to combine multiple WeChat messages (text, images, files) into a single agent request to avoid triggering multiple separate turns.

Who it’s for

Developers and power users who want to access their local AI agents or CLI-based AI tools via a mobile messaging interface, or those who want to automate AI interactions through WeChat using local injection commands.

Highlights

  • Multi-Agent Support: Includes built-in presets for popular agents like Claude, Gemini, Qwen, and Copilot.
  • Session Management: Supports isolated sessions per user with optional persistence across restarts.
  • Rich Media Handling: Forwards images, audio, and files between WeChat and the agent; saves received binary files to disk for agent access.
  • Bridge Commands: Built-in slash commands for session resets (/acp-new), turn cancellation (/acp-cancel), and configuration (/acp-config).
  • Local Injection: Allows external scripts or cron jobs to enqueue messages for the agent to process and reply via WeChat.
  • Instance Isolation: Ability to run multiple bridge instances with different WeChat accounts and project directories.

Related

  • Project
    UNLINEARITY/CLI-WeChat-Bridge

    A bridge that connects WeChat to local AI CLI tools like Claude Code and Codex, allowing remote interaction and approval of local AI agents via mobile.

  • 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
    chenhg5/cc-connect

    cc‑connect is an open‑source bridge that lets you run AI agents (Kimi, Claude, Copilot CLI, etc.) on your own machine and control them from chat apps like Slack, Discord, Telegram, Feishu, QQ, and more. It forwards messages to the local agent, returns the agent’s response, and supports many platforms and agents out‑of‑the‑box.

  • Project
    aannoo/hcom

    A CLI tool that enables different AI coding agents to message, observe, and spawn each other across terminals to coordinate complex development workflows.

  • Project
    bcurts/agentchattr

    A local chat server that enables real-time coordination between humans and multiple AI coding agents, eliminating the need to copy-paste prompts between terminals.