🦞 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.

This checkout keeps that upstream OpenClaw base and adds a local companion stack for a more embodied, desktop-first assistant: local VOICEVOX speech, microphone input, Desktop Companion animation, FBX/VRM avatar control, LINE/Telegram readiness tooling, and Hypura Harness tools that agents can operate without guessing raw HTTP routes.

If you want a personal, single-user assistant that feels local, fast, always-on, and present on your desktop, 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 · 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.

Local companion and fork features

The fork-specific layer is intentionally local-first. It is built for the operator's own desktop, avatar assets, voice devices, and channel state. Keep credentials, raw channel ids, voice recordings, and private avatar files out of git.

• Desktop Companion for Live2D, FBX, and VRM: extensions/live2d-companion

can load local avatar assets, report avatar state, capture the companion window, and animate expression or motion when the AI speaks. VRM/FBX avatars use native expressions where possible and procedural motion fallback when a model has no matching animation clip.

• VOICEVOX speech with Kasukabe Tsumugi: extensions/local-voice and the

companion bridge default to VOICEVOX speaker 8 for a less mechanical local voice path. The renderer avoids silently falling back to browser Web Speech when VOICEVOX is explicitly selected.

• Local STT and consent controls: the companion and Hypura voice bridge

expose microphone permission, mic start/stop, input_snapshot, WAV transcription, and voice-turn tools. Agents must use the permission path before enabling capture.

• LINE and Telegram normalization: the LINE plugin normalizes real

U/C/R recipient ids after line:* prefixes are stripped, and Telegram resolves legacy ${TELEGRAM_BOT_TOKEN} env templates before trying to send. The channel skills document webhook, mention-gating, and live-proof steps.

• Hypura Harness as the agent bridge: extensions/hypura-harness exposes

redacted channel readiness, voice devices, VOICEVOX test speech, WAV transcription, companion controls, and companion voice turns as OpenClaw tools. GET /channels/readiness separates credential presence from real roundtrip readiness without printing tokens or raw routing ids.

• VRChat own-avatar OSC path: extensions/vrchat-relay and Hypura Harness

stay on the official OSC route. Existing-avatar control is profile-gated, local-only, rate-limited, and does not log in to VRChat, modify the client, or load remote avatar assets.

• Companion3D fallback body: the Hypura companion layer can keep a

local-only 3D companion body available when a VRChat profile is missing or unapproved.

Useful entry points:

• Desktop Companion guide:

extensions/live2d-companion/skills/desktop-companion/SKILL.md

• Local voice guide:

extensions/local-voice/skills/local-voice/SKILL.md

• Hypura voice and readiness guides:

extensions/hypura-harness/skills/voice-io/SKILL.md and

extensions/hypura-harness/skills/channel-readiness/SKILL.md

• LINE and Telegram channel guides:

extensions/line/skills/line-channel/SKILL.md and

extensions/telegram/skills/telegram-channel/SKILL.md

• VRChat existing-avatar and Companion3D guides:

extensions/hypura-harness/skills/vrchat-existing-avatar/SKILL.md and

extensions/hypura-harness/skills/desktop-companion-3d/SKILL.md

For a development checkout, the fastest local proof loop is:

node scripts/build-all.mjs gatewayWatch
node openclaw.mjs --profile desktop-stack channels status --json

Use hypura_harness_channel_readiness or GET /channels/readiness before claiming LINE or Telegram live roundtrip readiness; a configured token is not the same thing as a sendable target.

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

openclaw onboard --install-daemon

openclaw gateway --port 18789 --verbose

# 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

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, 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, 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)

Use pnpm for source checkouts. The repository is a pnpm workspace, and bundled plugins load from extensions/* during development so their package-local dependencies and your edits are used directly. Plain npm install at the repo root is not a supported source setup.

For the dev loop:

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 Control UI before first startup
pnpm ui:build

# Dev loop (auto-reload on source/config changes)
pnpm gateway:watch

If you need a built dist/ from the checkout (for Node, packaging, or release validation), run:

pnpm build
pnpm ui:build

pnpm openclaw setup writes the local config/workspace needed for pnpm gateway:watch. It is safe to re-run, but you normally only need it on first setup or after resetting local state. pnpm gateway:watch does not rebuild dist/control-ui, so rerun pnpm ui:build after ui/ changes or use pnpm ui:dev when iterating on the Control UI. If you want this checkout to run onboarding directly, use pnpm openclaw onboard --install-daemon.

Note: pnpm openclaw ... runs TypeScript directly (via tsx). pnpm build produces dist/ for running via Node / the packaged openclaw binary, while pnpm gateway:watch rebuilds the runtime on demand during the dev loop.

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)                                                                                                                                                                                                                                                                                                                                ![zhumengzhu](https://