Automation
Plugin
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.
Plugin Signal73/100Solid
maintained97
capable55
documented75
adopted53
Install
$ npx -y skills add 0xranx/golembot --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
315
Stars
42
Forks
Active
Maintenance
TypeScript
Language
MIT
License
6d ago
Last commit
5mo ago
Created
Repo: 0xranx/golembot
What's inside
Skills
13/escalationEscalate unresolvable or sensitive requests to a human agent by recording an escalation entry. Use when the user asks to speak to a human, the bot cannot answer confidently, the request involves financial, legal, or security concerns, a safety issue is detected, or the user is/generalHandle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember/im-adapterFormat responses for instant messaging platforms such as Lark, DingTalk, WeCom, Slack, and Telegram. Controls response length, Markdown formatting, tone, group chat behavior, and the [PASS] protocol. Use when replying through an IM channel, composing a group chat message, or/kb-guideSearch, read, create, and update knowledge base entries via MCP-connected KB tools. Use when the user asks to look up documentation, find existing articles, check if docs exist on a topic, create a new KB entry, update an existing document, or when domain questions should be/message-pushSend proactive messages to IM groups or individual users via the gateway Send API. Use when the user says to send, post, notify, forward, or tell someone a message on Feishu, Slack, Telegram, Discord, DingTalk, or WeCom./multi-botCoordinates responses between multiple GolemBot instances in a shared fleet. Use when the bot operates in a group chat with other bots, needs to decide whether to respond or pass, or must call a peer bot's API to fetch cross-domain data.
Show all 13 skillsShow fewer
/task-managerCreates and manages scheduled tasks, cron jobs, recurring reminders, and timers via the Task HTTP API. Use when the user asks to schedule something, set a recurring reminder, run a periodic check, or manage existing scheduled tasks./code-reviewReviews code changes, pull requests, and diffs for correctness, security, performance, and style. Use when the user submits a PR for review, asks to review a diff or code snippet, or requests a quality check on recent changes./faq-supportAnswers common customer questions from a knowledge base and escalates to a human agent when unable to help. Use when the user asks a frequently asked question, submits a support ticket or help desk request, or needs assistance with account, billing, or product issues./data-analysisLoads CSV, Excel, and JSON data files, performs statistical analysis, and generates charts and reports. Use when the user asks to analyze a dataset, compute statistics, create visualizations, find trends, or produce a data report./meetingMeeting notes assistant — organizes transcripts into structured minutes, extracts action items, and tracks attendee decisions. Use when the user asks to summarize a meeting, take meeting notes, write up minutes, create a meeting recap, list attendees, or extract action items/opsContent operations assistant — drafts blog posts, social media copy, and marketing materials, compiles data briefings, and tracks competitor activity. Use when the user asks to write a blog post, draft social media content, create marketing copy, generate a weekly report,/researchResearch assistant — gathers information, performs competitive analysis, and generates structured research reports. Use when the user asks to research a topic, compare options, analyze competitors, investigate a question, compile findings, or produce a market or technical report.
README
1Cursor, 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, WeChat, or any HTTP client — with any LLM provider. Route Claude Code through OpenRouter, run Codex on MiniMax, or point OpenCode at DeepSeek — one config block, zero code changes. 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, WeChat
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 |
| Provider freedom | 4 engines × any provider — OpenRouter, MiniMax, DeepSeek, SiliconFlow. One config block. | Locked to one LLM provider per framework |
| Skills | 13,000+ community skills from ClawHub, one command to install | Write your own tools and prompts from scratch |
| Scheduled tasks | Built-in cron scheduler — daily standups, dependency audits, test reports pushed to IM | Build your own job system |
| Multimodal | Image messages from IM → saved to disk → agent reads and analyzes. All 7 channels supported. | Parse platform APIs yourself |
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
Long task still running? Use /stop in REPL or IM, assistant.cancel(sessionKey?) in code, or POST /abort over HTTP to cancel the current task without clearing session history.
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 / WeChat / HTTP API
Custom Adapters (email, GitHub Issues, ...)
│
▼
┌─────────────────────────┐
│ Gateway Service │
│ (Channel adapters + │
│ HTTP service) │
└────────────┬────────────┘
│
createAssistant()
│
┌───────┬───────┬───────┐
▼ ▼ ▼ ▼
Cursor Claude OpenCode Codex
Code
↕ Provider Routing (OpenRouter, MiniMax, ...)
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 | CODEX_API_KEY (preferred) / ChatGPT OAuth |
| Runtime Mode | --force --trust --sandbox disabled | --dangerously-skip-permissions | permission config | default unrestricted; also supports sandbox / approval / search / addDirs |
The StreamEvent interface is identical across all engines — switching requires zero code changes.
If you run Codex, note that GolemBot defaults to codex.mode: unrestricted. Set codex.mode: safe if you want to keep Codex sandboxed. You can also use fine-grained codex.sandbox, codex.approval, codex.search, and codex.addDirs settings.
If you route Codex through a custom provider, that provider must support the OpenAI Responses API. Providers that only expose /chat/completions or Anthropic-style /messages endpoints will fail. See the Provider Routing guide: https://0xranx.github.io/golembot/guide/provider-routing#codex-requires-responses-api
Configuration
golem.yaml — the single config file:
name: my-assistant
engine: claude-code
# Optional: route engine to a third-party LLM provider
provider:
baseUrl: "https://openrouter.ai/api"
apiKey: "${OPENROUTER_API_KEY}"
model: "anthropic/claude-sonnet-4"
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}
# domain: lark # optional — Lark global tenants
# pingTimeout: 30 # optional — WebSocket pong timeout in seconds
# Custom adapter — local file or npm package
my-email:
_adapter: ./adapters/email-adapter.js
token: ${EMAIL_TOKEN}
# Optional: Codex runtime controls (Codex engine only)
codex:
mode: unrestricted # compatibility alias; set safe to keep sandboxing
sandbox: workspace-write
approval: on-request
search: true
addDirs:
- ../shared-assets
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)
pnpm run e2e:codex:launch # Real Codex launch verification (flags, resume, HTTP path)
Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
License
File tree
4800xranx/golembotView on GitHub
.cursor/
rules/
architecture-constraints.mdc
engine-internals.mdc
testing-conventions.mdc
.dockerignore
.env.example
.github/
ISSUE_TEMPLATE/
bug_report.md
feature_request.md
PULL_REQUEST_TEMPLATE.md
workflows/
ci.yml
docs.yml
release.yml
windows-spawn-smoke.yml
.gitignore
.husky/
pre-commit
.npmignore
.npmrc
.releaserc.json
AGENTS.md
biome.json
CHANGELOG.md
CLAUDE.md
CONTRIBUTING.md
dist/
channel.d.ts
channel.d.ts.map
channel.js
channel.js.map
channels/
dingtalk.d.ts
dingtalk.d.ts.map
dingtalk.js
dingtalk.js.map
discord.d.ts
discord.d.ts.map
discord.js
discord.js.map
feishu-format.d.ts
feishu-format.d.ts.map
feishu-format.js
feishu-format.js.map
feishu.d.ts
feishu.d.ts.map
feishu.js
feishu.js.map
slack-format.d.ts
slack-format.d.ts.map
slack-format.js
slack-format.js.map
slack.d.ts
slack.d.ts.map
slack.js
slack.js.map
telegram-format.d.ts
telegram-format.d.ts.map
telegram-format.js
telegram-format.js.map
telegram.d.ts
telegram.d.ts.map
telegram.js
telegram.js.map
wecom.d.ts
wecom.d.ts.map
wecom.js
wecom.js.map
weixin.d.ts
weixin.d.ts.map
weixin.js
weixin.js.map
cli-utils.d.ts
cli-utils.d.ts.map
cli-utils.js
cli-utils.js.map
cli.d.ts
cli.d.ts.map
cli.js
cli.js.map
codex-provider-compat.d.ts
codex-provider-compat.d.ts.map
codex-provider-compat.js
codex-provider-compat.js.map
commands.d.ts
commands.d.ts.map
commands.js
commands.js.map
dashboard.d.ts
dashboard.d.ts.map
dashboard.js
dashboard.js.map
doctor.d.ts
doctor.d.ts.map
doctor.js
doctor.js.map
engine.d.ts
engine.d.ts.map
engine.js
engine.js.map
engines/
claude-code.d.ts
claude-code.d.ts.map
claude-code.js
claude-code.js.map
codex.d.ts
codex.d.ts.map
codex.js
codex.js.map
cursor.d.ts
cursor.d.ts.map
cursor.js
cursor.js.map
opencode.d.ts
opencode.d.ts.map
opencode.js
opencode.js.map
provider-env.d.ts
provider-env.d.ts.map
provider-env.js
provider-env.js.map
shared.d.ts
shared.d.ts.map
shared.js
shared.js.map
fleet.d.ts
fleet.d.ts.map
fleet.js
fleet.js.map
gateway.d.ts
gateway.d.ts.map
gateway.js
gateway.js.map
history-fetcher.d.ts
history-fetcher.d.ts.map
history-fetcher.js
history-fetcher.js.map
image-compress.d.ts
image-compress.d.ts.map
image-compress.js
image-compress.js.map
inbox.d.ts
inbox.d.ts.map
inbox.js
inbox.js.map
index.d.ts
index.d.ts.map
index.js
index.js.map
onboard.d.ts
onboard.d.ts.map
onboard.js
onboard.js.map
peer-require.d.ts
peer-require.d.ts.map
peer-require.js
peer-require.js.map
proactive.d.ts
proactive.d.ts.map
proactive.js
proactive.js.map
provider-presets.d.ts
provider-presets.d.ts.map
provider-presets.js
provider-presets.js.map
registry.d.ts
registry.d.ts.map
registry.js
registry.js.map
scheduler.d.ts
scheduler.d.ts.map
scheduler.js
scheduler.js.map
seen-messages.d.ts
seen-messages.d.ts.map
seen-messages.js
seen-messages.js.map
server.d.ts
server.d.ts.map
server.js
server.js.map
session.d.ts
session.d.ts.map
session.js
session.js.map
task-store.d.ts
task-store.d.ts.map
task-store.js
task-store.js.map
token-meta.d.ts
token-meta.d.ts.map
token-meta.js
token-meta.js.map
ui-shared.d.ts
ui-shared.d.ts.map
ui-shared.js
ui-shared.js.map
weixin-login.d.ts
weixin-login.d.ts.map
weixin-login.js
weixin-login.js.map
workspace.d.ts
workspace.d.ts.map
workspace.js
workspace.js.map
docker-compose.yml
Dockerfile
docs/
.vitepress/
config.ts
theme/
custom.css
index.ts
api/
channel-adapter.md
create-assistant.md
http-api.md
stream-events.md
assets/
dashboard.png
demo.mp4
feishu-chat.png
fleet-dashboard.png
logo-golem-dark.svg
logo-golem-light.svg
skill-search.png
social-preview.svg
weixin-image.jpg
weixin-text.png
weixin-voice.jpg
channels/
dingtalk.md
discord.md
feishu.md
overview.md
slack.md
telegram.md
wecom.md
weixin.md
drafts/
wechat-article-outline.md
wechat-article.md
engines/
claude-code.md
codex.md
cursor.md
opencode.md
overview.md
faq.md
guide/
cli-commands.md
configuration.md
dashboard.md
docker.md
embed.md
getting-started.md
group-chat.md
inbox.md
memory.md
onboard-wizard.md
provider-routing.md
scheduled-tasks.md
index.md
launch-copy.md
public/
assets/
dashboard.png
fleet-dashboard.png
icons/
claude.svg
claw.svg
clawhub.png
cpu.svg
cursor.svg
dingtalk.svg
discord.svg
feishu.svg
folder.svg
opencode.svg
plug.svg
slack.svg
telegram.svg
wecom.svg
weixin.svg
logo-dark.svg
logo-icon-dark.svg
logo-icon-light.svg
logo-light.svg
og-image.png
og-image.svg
robots.txt
reference/
architecture.md
coding-cli-claude-code.md
coding-cli-codex.md
coding-cli-comparison.md
coding-cli-cursor.md
coding-cli-docs.md
coding-cli-opencode.md
skills/
builtin.md
create-skill.md
overview.md
testing/
im-playbook.md
issues.md
todo/
bugs-and-debt.md
enhancements.md
phase3-features.md
README.md
zh/
api/
channel-adapter.md
create-assistant.md
http-api.md
stream-events.md
channels/
dingtalk.md
discord.md
feishu.md
overview.md
slack.md
telegram.md
wecom.md
weixin.md
engines/
claude-code.md
codex.md
cursor.md
opencode.md
overview.md
faq.md
guide/
cli-commands.md
configuration.md
dashboard.md
docker.md
embed.md
getting-started.md
group-chat.md
inbox.md
memory.md
onboard-wizard.md
provider-routing.md
scheduled-tasks.md
index.md
reference/
architecture.md
coding-cli-claude-code.md
coding-cli-codex.md
coding-cli-comparison.md
coding-cli-cursor.md
coding-cli-docs.md
coding-cli-opencode.md
skills/
builtin.md
create-skill.md
overview.md
testing/
im-playbook.md
issues.md
examples/
e2e-claude-code.ts
e2e-codex-launch.ts
e2e-codex.ts
e2e-headless.ts
e2e-opencode.ts
e2e-test.ts
feishu-format-demo.ts
im-format-test.ts
im-image-test.ts
multi-bot-group/
.gitignore
adapters/
mock-group-adapter.mjs
bot-a/
golem.yaml
skills/
researcher/
SKILL.md
bot-b/
golem.yaml
skills/
coder/
SKILL.md
README.md
run.mjs
golem.yaml
LICENSE
notes.md
package.json
pnpm-lock.yaml
pnpm-workspace.yaml
README.md
README.zh-CN.md
skills/
escalation/
... 154 moreFAQ
golembot is a Claude Code plugin with 13 hand-picked skills for automation work, indexed on Flowy. Install it with the command on its page. It includes escalation, general, im-adapter. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is 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.
- How do I install golembot?
- Run these in Claude Code: npx -y skills add 0xranx/golembot --agent claude-code. Then prompt normally.
- Does golembot auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is golembot free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.