0xranx/golembot

Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

What it solves

GolemBot provides a way to take existing "Coding Agents" (like Cursor, Claude Code, OpenCode, and Codex) and deploy them as accessible assistants on messaging platforms. It removes the need to build a custom AI framework or write complex prompt engineering from scratch by using these battle-tested agents as the "brain" and providing a standardized gateway to connect them to external interfaces.

How it works

GolemBot acts as a gateway service that wraps around a chosen agent engine. It translates messages from various communication channels (Slack, Telegram, Discord, etc.) into a format the agent can understand and streams the agent's responses back to the user. It supports provider routing, allowing users to route these agents through third-party LLM providers like OpenRouter or DeepSeek via a single configuration file (golem.yaml).

Who it’s for

It is designed for developers and teams who want to integrate powerful coding agents into their team communication tools or embed agentic capabilities into their own Node.js products without building the entire agent logic from scratch.

Highlights

  • Multi-Channel Support: Native integration with Slack, Telegram, Discord, Feishu, DingTalk, WeCom, and WeChat.
  • Engine Agnostic: Compatible with Cursor, Claude Code, OpenCode, and Codex, allowing users to swap engines with one line of config.
  • Skill Ecosystem: Integration with ClawHub, providing access to over 13,000 community-created skills that can be installed via a single command.
  • Built-in Management: Includes a web Dashboard for real-time metrics and a Fleet Dashboard for managing multiple bots.
  • Customizable: Supports custom channel adapters for sources like email or GitHub Issues and a built-in cron scheduler for automated tasks.

Related

  • Project
    xianyu110/clawbot

    Clawdbot is an open‑source, locally‑run AI assistant that connects to Claude, GPT, Gemini and other LLMs via configurable API‑proxy endpoints. It offers web and terminal UIs, Telegram/Discord/WhatsApp bots, and stores all data on the host. The README covers installation (Node 22+, npm or script), an onboarding wizard for model and channel setup, detailed JSON configuration for multi‑model proxies, common pitfalls (Node version, env‑var misuse, missing fields), and a full set of CLI commands for managing the gateway, logs, and diagnostics.

  • Project
    yincongcyincong/MuseBot

    MuseBot is a Go‑based, multi‑platform chatbot that forwards messages from Telegram, Discord, Slack, Lark, DingTalk, Enterprise WeChat, QQ, WeChat, or a generic Web API to a chosen LLM (OpenAI, DeepSeek, Gemini, etc.) and streams the AI’s reply back. It supports image/voice input, function‑call bridging, skill templates, RAG, admin UI, metrics, and cron‑triggered prompts. Install via `go run` or Docker, configure with environment variables, and you’re ready to add AI to any chat service.

  • Dispatch
    CopilotKit Channels SDK Open-Source Release Enables Any AI Agent on Slack, Teams, Discord, and More

    CopilotKit released the open-source Channels SDK, letting developers attach any AG‑UI‑compatible AI agent to Slack, Microsoft Teams, Discord, Telegram and other chat platforms with native interactive UI.

  • Project
    corespeed-io/wechatbot

    A modular, production-grade SDK for connecting AI agents to WeChat via the iLink protocol, supporting Node.js, Python, Go, and Rust.

  • Project
    Zero6992/chatGPT-discord-bot

    A self-hosted Discord bot that integrates multiple AI providers and local models into one interface, supporting persistent chat history and media generation.