codex

🦞 OpenClaw — Personal AI Assistant

<p align="center"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/openclaw-logo-text-dark.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/openclaw-logo-text.svg" alt="OpenClaw" width="500"> </picture> </p>

<p align="center"> <strong>EXFOLIATE! EXFOLIATE!</strong> </p>

<p align="center"> <a href="https://github.com/openclaw/openclaw/actions/workflows/ci.yml?branch=main"><img src="https://img.shields.io/github/actions/workflow/status/openclaw/openclaw/ci.yml?branch=main&style=for-the-badge" alt="CI status"></a> <a href="https://github.com/openclaw/openclaw/releases"><img src="https://img.shields.io/github/v/release/openclaw/openclaw?include_prereleases&style=for-the-badge" alt="GitHub release"></a> <a href="https://discord.gg/clawd"><img src="https://img.shields.io/discord/1456350064065904867?label=Discord&logo=discord&logoColor=white&color=5865F2&style=for-the-badge" alt="Discord"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge" alt="MIT License"></a> </p>

OpenClaw is a _personal AI assistant_ you run on your own devices. It answers you on the channels you already use. It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.

If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.

Supported channels include: WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, QQ, WebChat.

Website · Docs · Vision · Third-party notices · DeepWiki · Getting Started · Updating · Showcase · FAQ · Onboarding · Nix · Docker · Discord

New install? Start here: Getting started

Preferred setup: run openclaw onboard in your terminal. OpenClaw Onboard guides you step by step through setting up the gateway, workspace, channels, and skills. It is the recommended CLI setup path and works on macOS, Linux, and Windows (via WSL2; strongly recommended). Works with npm, pnpm, or bun.

Sponsors

<table> <tr> <td align="center" width="16.66%"> <a href="https://openai.com/"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/openai-light.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/openai.svg" alt="OpenAI" height="28"> </picture> </a> </td> <td align="center" width="16.66%"> <a href="https://github.com/"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/github-light.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/github.svg" alt="GitHub" height="28"> </picture> </a> </td> <td align="center" width="16.66%"> <a href="https://www.nvidia.com/"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/nvidia.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/nvidia-dark.svg" alt="NVIDIA" height="28"> </picture> </a> </td> <td align="center" width="16.66%"> <a href="https://vercel.com/"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/vercel-light.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/vercel.svg" alt="Vercel" height="24"> </picture> </a> </td> <td align="center" width="16.66%"> <a href="https://blacksmith.sh/"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/blacksmith-light.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/blacksmith.svg" alt="Blacksmith" height="28"> </picture> </a> </td> <td align="center" width="16.66%"> <a href="https://www.convex.dev/"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/convex-light.svg"> <img src="https://raw.githubusercontent.com/openclaw/openclaw/main/docs/assets/sponsors/convex.svg" alt="Convex" height="24"> </picture> </a> </td> </tr> </table>

Subscriptions (OAuth):

• OpenAI (ChatGPT/Codex)

Model note: while many providers and models are supported, prefer a current flagship model from the provider you trust and already use. See Onboarding.

Install (recommended)

Runtime: Node 24 (recommended) or Node 22.19+.

npm install -g openclaw@latest
# or: pnpm add -g openclaw@latest

openclaw onboard --install-daemon

OpenClaw Onboard installs the Gateway daemon (launchd/systemd user service) so it stays running.

Quick start (TL;DR)

Runtime: Node 24 (recommended) or Node 22.19+.

Full beginner guide (auth, pairing, channels): Getting started

Recommended daemon mode:

openclaw onboard --install-daemon
openclaw gateway status

Foreground/debug mode:

openclaw gateway stop
openclaw gateway --port 18789 --verbose

Send a test message or ask the assistant after either startup mode is running:

# Send a message
openclaw message send --target +1234567890 --message "Hello from OpenClaw"

# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/IRC/Microsoft Teams/Matrix/Feishu/LINE/Mattermost/Nextcloud Talk/Nostr/Synology Chat/Tlon/Twitch/Zalo/Zalo Personal/WeChat/QQ/WebChat)
openclaw agent --message "Ship checklist" --thinking high

Upgrading? Updating guide (and run openclaw doctor).

Models config + CLI: Models. Auth profile rotation + fallbacks: Model failover.

Security defaults (DM access)

OpenClaw connects to real messaging surfaces. Treat inbound DMs as untrusted input.

Full security guide: Security. Before remote exposure, use the Gateway exposure runbook.

Default behavior on Telegram/WhatsApp/Signal/iMessage/Microsoft Teams/Discord/Google Chat/Slack:

• DM pairing (dmPolicy="pairing" / channels.discord.dmPolicy="pairing" / channels.slack.dmPolicy="pairing"; legacy: channels.discord.dm.policy, channels.slack.dm.policy): unknown senders receive a short pairing code and the bot does not process their message.
• Approve with: openclaw pairing approve <channel> <code> (then the sender is added to a local allowlist store).
• Public inbound DMs require an explicit opt-in: set dmPolicy="open" and include "*" in the channel allowlist (allowFrom / channels.discord.allowFrom / channels.slack.allowFrom; legacy: channels.discord.dm.allowFrom, channels.slack.dm.allowFrom).

Run openclaw doctor to surface risky/misconfigured DM policies.

Highlights

• Local-first Gateway — single control plane for sessions, channels, tools, and events.
• Multi-channel inbox — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, QQ, WebChat, macOS, iOS/Android.
• Multi-agent routing — route inbound channels/accounts/peers to isolated agents (workspaces + per-agent sessions).
• Voice Wake + Talk Mode — wake words on macOS/iOS and continuous voice on Android (ElevenLabs + system TTS fallback).
• Live Canvas — agent-driven visual workspace with A2UI.
• First-class tools — browser, canvas, nodes, cron, sessions, and Discord/Slack actions.
• Companion apps — macOS menu bar app + iOS/Android nodes.
• Onboarding + skills — onboarding-driven setup with bundled/managed/workspace skills.

Security model (important)

• Default: tools run on the host for the main session, so the agent has full access when it is just you.
• Group/channel safety: set agents.defaults.sandbox.mode: "non-main" to run non-main sessions inside sandboxes. Docker is the default sandbox backend; SSH and OpenShell backends are also available.
• Typical sandbox default: allow bash, process, read, write, edit, sessions_list, sessions_history, sessions_send, sessions_spawn; deny browser, canvas, nodes, cron, discord, gateway.
• Before exposing anything remotely, read Security, Gateway exposure runbook, Sandboxing, and Configuration.

Operator quick refs

• Chat commands: /status, /new, /reset, /compact, /think <level>, /verbose on|off, /trace on|off, /usage off|tokens|full, /restart, /activation mention|always
• Session tools: sessions_list, sessions_history, sessions_send
• Skills registry: ClawHub
• Architecture overview: Architecture

Docs by goal

• New here: Getting started, Onboarding, Updating
• Channel setup: Channels index, WhatsApp, Telegram, Discord, Slack
• Apps + nodes: macOS, iOS, Android, Nodes
• Config + security: Configuration, Security, Exposure runbook, Sandboxing
• Remote + web: Gateway, Remote access, Tailscale, Web surfaces
• Tools + automation: Tools, Skills, Cron jobs, Webhooks, Gmail Pub/Sub
• Internals: Architecture, Agent, Session model, Gateway protocol
• Troubleshooting: Channel troubleshooting, Logging, Docs home

Apps (optional)

The Gateway alone delivers a great experience. All apps are optional and add extra features.

If you plan to build/run companion apps, follow the platform runbooks below.

macOS (OpenClaw.app) (optional)

• Menu bar control for the Gateway and health.
• Voice Wake + push-to-talk overlay.
• WebChat + debug tools.
• Remote gateway control over SSH.

Note: signed builds required for macOS permissions to stick across rebuilds (see macOS Permissions).

iOS node (optional)

• Pairs as a node over the Gateway WebSocket (device pairing).
• Voice trigger forwarding + Canvas surface.
• Controlled via openclaw nodes ….

Runbook: iOS connect.

Android node (optional)

• Pairs as a WS node via device pairing (openclaw devices ...).
• Exposes Connect/Chat/Voice tabs plus Canvas, Camera, Screen capture, and Android device command families.
• Runbook: Android connect.

From source (development)

Source checkouts require Node 24 (recommended) or Node 22.19+ and the workspace-pinned pnpm version. This repo is a pnpm workspace: bundled plugins load from extensions/* during development, so root npm install does not prepare the full source tree.

First run

git clone https://github.com/openclaw/openclaw.git
cd openclaw

pnpm install

# First run only (or after resetting local OpenClaw config/workspace)
pnpm openclaw setup

# Optional: prebuild the Control UI before first Gateway startup
pnpm ui:build

Gateway dev modes

| Command | Use when | | --------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | | pnpm gateway:watch | You want the normal hot-reload Gateway loop. It runs in a named tmux session and auto-attaches from interactive terminals. | | pnpm gateway:watch:raw | You want the same Gateway watch loop in the foreground, without tmux. | | OPENCLAW_GATEWAY_WATCH_ATTACH=0 pnpm gateway:watch | You want tmux-managed watch mode but do not want the current terminal to attach. | | OPENCLAW_GATEWAY_WATCH_AUTO_DOCTOR=0 pnpm gateway:watch | You want to see the original startup failure instead of the dev-only openclaw doctor --fix --non-interactive retry. | | pnpm gateway:dev | You want an isolated dev profile with channels skipped. | | pnpm gateway:dev:reset | You want to reset that isolated dev profile before starting it. |

The usual Gateway loop is:

pnpm gateway:watch

The Gateway WebSocket defaults to ws://127.0.0.1:18789; keep the app and CLI on the same port. If you are also running the macOS app, set Connection Mode to

Local so it attaches to the Gateway from this checkout.

Control UI dev mode

For backend + UI development, use two terminals:

# Terminal 1, from the repo root
pnpm gateway:watch

# Terminal 2, from the repo root
pnpm ui:dev

pnpm ui:dev starts the Vite Control UI dev server. The default Vite port is

5173; if another server already uses it, choose another port:

pnpm ui:dev -- --port 5174

You can also run the UI package script directly:

cd ui
pnpm dev

pnpm gateway:watch does not rebuild dist/control-ui. When changing ui/, use

pnpm ui:dev for hot reload or run pnpm ui:build before testing the built UI served from dist/control-ui.

Build and checks

# Build the repo output used by Node/package validation
pnpm build

# Build the production Control UI bundle
pnpm ui:build

# Run focused tests
pnpm test <path-or-filter>

# Run changed checks
pnpm check:changed

pnpm openclaw ... runs TypeScript directly via the dev loader. pnpm build produces dist/ for running through Node or the packaged openclaw binary, while

pnpm gateway:watch rebuilds the runtime on demand during the dev loop.

Local environment gotchas

• If pnpm warns that Node is too old or crashes with ERR_UNKNOWN_BUILTIN_MODULE: node:sqlite, the terminal is using Node 20 or older. Switch that terminal to Node 22.19+ or Node 24 before running pnpm.
• In read-only or Nix-style environments, corepack enable can fail because it tries to create package-manager shims under a read-only system path. Use a shell where Node 22.19+/24 and the workspace-pinned pnpm are both on PATH, or install pnpm into a writable user prefix.
• If Vite reports Port 5173 is already in use, stop the old dev server or pass another port with pnpm ui:dev -- --port 5174.

Full source setup details: Setup.

Development channels

• stable: tagged releases (vYYYY.M.D or vYYYY.M.D-<patch>), npm dist-tag latest.
• beta: prerelease tags (vYYYY.M.D-beta.N), npm dist-tag beta (macOS app may be missing).
• dev: moving head of main, npm dist-tag dev (when published).

Switch channels (git + npm): openclaw update --channel stable|beta|dev. Details: Development channels.

Agent workspace + skills

• Workspace root: ~/.openclaw/workspace (configurable via agents.defaults.workspace).
• Injected prompt files: AGENTS.md, SOUL.md, TOOLS.md.
• Skills: ~/.openclaw/workspace/skills/<skill>/SKILL.md.

Configuration

Minimal ~/.openclaw/openclaw.json (model + defaults):

{
  agent: {
    model: "<provider>/<model-id>",
  },
}

Full configuration reference (all keys + examples).

Star History


Molty

OpenClaw was built for Molty, a space lobster AI assistant. 🦞 by Peter Steinberger and the community.

• openclaw.ai
• soul.md
• steipete.me
• @openclaw

Community

See CONTRIBUTING.md for guidelines, maintainers, and how to submit PRs. AI/vibe-coded PRs welcome! 🤖

Special thanks to Mario Zechner for his support and for pi-mono. Special thanks to Adam Doppelt for the lobster.bot domain.

Thanks to all clawtributors:

<!-- clawtributors:start -->

                                                         [![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&s=48)](https://github.com/apps/github-actions)                                                                                                                                                                                                                                                                                                                                    [![Tanwa