English | 中文

Your Coding Agent is trapped in a terminal. GolemBot sets it free.

Compatible with 13,000+ OpenClaw community skills — the largest AI agent skill ecosystem. One command to search and install.

📖 Documentation & Guides → 0xranx.github.io/golembot

---

Cursor, Claude Code, OpenCode, Codex — these Coding Agents can already write code, run scripts, analyze data, and reason through complex tasks. But they're stuck in an IDE or a terminal window.

GolemBot gives them a body. One command connects your Coding Agent to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, or any HTTP client. Write a custom adapter to plug in email, GitHub Issues, or any other message source. Or embed into your own product with 5 lines of code. No AI framework, no prompt engineering — the agent you already have is the brain.

Run Your Coding Agent Everywhere

On IM — your team's 24/7 AI teammate

golembot init -e claude-code -n my-bot
golembot gateway    # Slack, Telegram, Discord, Feishu, DingTalk, WeCom

Your colleagues @ the bot in group chat. It can write code, analyze files, answer questions — because behind it is a real Coding Agent, not a thin API wrapper.

In your product — full agent power, 5 lines of code

import { createAssistant } from 'golembot';
const bot = createAssistant({ dir: './my-agent' });
for await (const event of bot.chat('Analyze last month sales data')) {
if (event.type === 'text') process.stdout.write(event.content);
}

Embed into Slack bots, internal tools, SaaS products, customer support — anything that speaks Node.js.

Why GolemBot, not another AI framework?

	GolemBot	Traditional AI Frameworks
AI brain	Cursor / Claude Code / OpenCode / Codex — battle-tested, full coding ability	You wire up LLM APIs + tools from scratch
Setup	golembot init → done	Chains, RAG, vector DB, prompt tuning...
Auto-upgrade	Agent gets smarter? Your assistant gets smarter. Zero code changes.	You maintain everything yourself
Transparency	ls the directory = see what the assistant knows and does	Black box pipelines
Engine lock-in	Change one line in config to swap engines	Rewrite everything
Skills	13,000+ community skills from ClawHub, one command to install	Write your own tools and prompts from scratch

Quick Start

npm install -g golembot
mkdir my-bot && cd my-bot
golembot onboard      # guided setup (recommended)
Or manually:
golembot init -e claude-code -n my-bot
golembot run          # REPL conversation
golembot gateway      # start IM + HTTP service + Dashboard
golembot fleet ls     # list all running bots
golembot skill search "data analysis"  # browse 13,000+ ClawHub skills

Dashboard & Fleet

Every golembot gateway instance comes with a built-in web Dashboard showing real-time metrics, channel status, and a quick-test console:

Running multiple bots? golembot fleet serve aggregates them into a single Fleet Dashboard:

Architecture

Slack / Telegram / Discord / Feishu / DingTalk / WeCom / HTTP API
    Custom Adapters (email, GitHub Issues, ...)
                    │
                    ▼
         ┌─────────────────────────┐
         │     Gateway Service     │
         │  (Channel adapters +    │
         │   HTTP service)         │
         └────────────┬────────────┘
                      │
              createAssistant()
                      │
          ┌───────┬───────┬───────┐
          ▼       ▼       ▼       ▼
       Cursor  Claude  OpenCode  Codex
               Code

Engine Comparison

	Cursor	Claude Code	OpenCode	Codex
Skill Injection	.cursor/skills/	.claude/skills/ + CLAUDE.md	.opencode/skills/ + opencode.json	AGENTS.md at workspace root
Session Resume	--resume	--resume	--session	exec resume <thread_id>
API Key	CURSOR_API_KEY	ANTHROPIC_API_KEY	Depends on Provider	OPENAI_API_KEY or ChatGPT OAuth

The StreamEvent interface is identical across all engines — switching requires zero code changes.

Configuration

golem.yaml — the single config file:

name: my-assistant
engine: claude-code
channels:
slack:
botToken: ${SLACK_BOT_TOKEN}
appToken: ${SLACK_APP_TOKEN}
telegram:
botToken: ${TELEGRAM_BOT_TOKEN}
discord:
botToken: ${DISCORD_BOT_TOKEN}
botName: my-assistant        # optional — normalizes @mention tokens in channel messages
feishu:
appId: ${FEISHU_APP_ID}
appSecret: ${FEISHU_APP_SECRET}
Custom adapter — local file or npm package
my-email:
_adapter: ./adapters/email-adapter.js
token: ${EMAIL_TOKEN}
gateway:
port: 3000
token: ${GOLEM_TOKEN}

Sensitive fields support ${ENV_VAR} references. Custom channel adapters can be local .js/.mjs files or npm packages — see the adapter guide.

Skill System

A Skill is a directory containing SKILL.md + optional scripts. Drop it in, the assistant gains new abilities. Remove it, the ability is gone.

skills/
├── general/          # Built-in: general assistant
│   └── SKILL.md
├── im-adapter/       # Built-in: IM reply conventions
│   └── SKILL.md
└── my-custom-skill/  # Your own
    ├── SKILL.md
    └── analyze.py

ls skills/ is the complete list of what your assistant can do.

13,000+ Skills from ClawHub

GolemBot is fully compatible with ClawHub — the largest AI agent skill marketplace by OpenClaw. The SKILL.md format is 100% compatible, so all 13,000+ community skills work out of the box.

golembot skill search "data analysis"       # discover skills
golembot skill add clawhub:data-analysis    # one command to install

Agent-powered skill discovery: Your agent can search and install skills autonomously during conversations. Ask it "find me a good code review skill" — it searches ClawHub, shows results, and installs on your confirmation.

All skill commands support --json for programmatic access. The pluggable registry interface supports additional skill sources beyond ClawHub.

Docker Deployment

FROM node:22-slim
RUN npm install -g golembot
WORKDIR /assistant
COPY . .
EXPOSE 3000
CMD ["golembot", "gateway"]

Development

git clone https://github.com/0xranx/golembot.git
cd golembot
pnpm install
pnpm run build
pnpm run test          # Unit tests (1252+)
pnpm run e2e:opencode  # End-to-end tests (OpenCode)
pnpm run e2e:codex     # End-to-end tests (Codex)

License

MIT