Open Claw setupGateway-firstSelf-hosted control

OpenClawsetupfor teamsthat wantfull control

The goal isn’t “it installs once.” The goal is an Open Claw deployment that stays stable when you add channels, tools, policies, and real team usage. Scroll for a buyer-grade overview, a setup playbook, quick commands, and the full openclaw.md at the bottom.

OpenClaw setup serviceGateway configurationChannel wiringDeployment hardening
OpenClaw stackSelf-hosted
Runtime
Node 22.16+ · npm · CLI
Control plane
Gateway on :18789
Surfaces
Channels · TUI · WebChat · voice
Positioning
Your stack · your workflows
OpenClaw runs as a local-first assistant layer: bring the gateway online, attach the channels you use, then iterate with agents and tools without giving up architectural ownership.
Scroll
Open Claw SetupOpenClaw installationGateway :18789Channel-nativeCLI · TUISelf-hosted controlGovernance + auditabilityFull docs below
Open Claw SetupOpenClaw installationGateway :18789Channel-nativeCLI · TUISelf-hosted controlGovernance + auditabilityFull docs below
Overview

Open Claw rollout that feels predictable, not fragile.

This page is intentionally built for setup intent (commands + steps), but also for decision intent (what you’re actually deploying and why it’s different from a quick demo).

Gateway-first

A control plane you actually own

Open Claw starts with a gateway so you can route tools, channels, and policy without duct-taping a dozen sidecars.

Channel-native

Ship into real workflows, not demos

Wire Slack/CLI/TUI/WebChat surfaces and keep behavior consistent across environments with one operating model.

Governance

Architecture that scales past the pilot

Auditability, runtime discipline, and predictable failure modes—so rollout doesn’t degrade into “it worked on my laptop.”

DIY route

If your team wants to build it

We’ll keep the page optimized for setup intent: clear steps, commands, and a full markdown reference so your engineers can self-serve.

Done-for-you

If you want it operational fast

We handle Open Claw setup, gateway configuration, channel wiring, and rollout hardening so your team stays focused on product outcomes.

Nemo Claw setup
Setup playbook

How to setup Open Claw without drifting into chaos.

The high-level moves: get a clean CLI baseline, bring the gateway online, stabilize one surface, then expand channels/tools with repeatable hardening.

Operational checklist
Ports
Gateway port is explicit and documented (no “random 3000 drift”).
Config
Single source of truth for policies and tool routing.
Secrets
Provider/API keys are stored outside repo and rotated.
Logs
Gateway + agent logs are structured and easy to grep.
Surfaces
One surface stable before adding the next channel.
Rollback
Update plan includes a clean revert path.
If you want us to implement this end-to-end and hand you a stable baseline, hit .
Step 01

Preflight: decide your operating model

Pick the first surface (CLI/TUI/WebChat), decide where secrets live, and define what “safe defaults” mean (tools allowed, network egress, file access).

Command snippet
# Suggested: create a clean working dir for configs
mkdir -p openclaw && cd openclaw
Step 02

Install + verify the CLI

Get to a clean baseline before touching gateway integrations. If the baseline is unstable, everything above it will be noisy.

Command snippet
npm install -g openclaw@latest
openclaw doctor
Step 03

Bring the gateway online

Gateway-first means one clear place to reason about routing, channels, and tools. Start verbose, then dial it back once stable.

Command snippet
openclaw gateway --port 18789 --verbose
Step 04

Onboard + connect a first surface

Get a single interaction surface stable before you add more. This is where most “random failures” originate (env, ports, permissions).

Command snippet
openclaw onboard
openclaw tui
Step 05

First agent loop + sanity test

Run a small prompt that forces tool usage (or forces it off). Your goal is to validate behavior, not impress yourself.

Command snippet
openclaw agent --message "Summarize current config + list available tools." --thinking high
Step 06

Hardening: logs, supervision, repeatability

Once it works once, make it work forever: structured logs, restart policy, and a predictable update path.

Command snippet
# Example placeholders – adapt to your environment
# systemctl enable openclaw-gateway
# systemctl restart openclaw-gateway
Quick commands

Copy-paste starters, with context.

These are the “fast path” commands people search for. The bottom of this page contains the full markdown reference.

Install

Install the CLI + daemon install path for local-first usage.

npm install -g openclaw@latest && openclaw onboard --install-daemon
Gateway

Bring the control plane online (default port shown).

openclaw gateway --port 18789 --verbose
Doctor

Sanity-check runtime assumptions before you debug ghosts.

openclaw doctor
Agent

First interaction test with explicit thinking level.

openclaw agent --message "Hello" --thinking high
If you want us to handle it

Open Claw deployment as a done-for-you rollout.

Setup is rarely the hard part. The hard part is making it operational when you add channels, policies, tools, and real team usage. If you want a stable baseline with documentation and a clean handoff, we can do the rollout end-to-end.

Compare platforms
FAQ

Questions teams ask before committing to an Open Claw setup.

Who is Open Claw setup for?

Teams that want architectural control: gateway-first routing, multiple interaction surfaces, and an operating model that stays sane as usage grows.

Is this page only documentation?

No—this is setup intent + buyer intent. The top half explains what you’re actually standing up, and the bottom includes the full markdown reference.

Do you help with Nemo Claw too?

Yes. If you want the faster “reference stack” style route, Nemo Claw can be the quicker baseline. Open Claw is for deeper customization and governance.

What does “done-for-you” typically include?

Environment prep, gateway configuration, channel wiring, workflow alignment, documentation, and rollout hardening so your internal team avoids setup drag.

Complete reference

Everything from openclaw.md— kept clean for long reads.

Scroll to documentation ↓

🦞 OpenClaw — Personal AI Assistant

OpenClaw is a personal AI assistant you run on your own devices. It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, WebChat). 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.

Website · Docs · Vision · DeepWiki · Getting Started · Updating · Showcase · FAQ · Onboarding · Nix · Docker · Discord

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. New install? Start here: Getting started

Subscriptions (OAuth):

Model note: while many providers/models are supported, for the best experience and lower prompt-injection risk use the strongest latest-generation model available to you. See Onboarding.

Models (selection + auth)

Install (recommended)

Runtime: Node 24 (recommended) or Node 22.16+.

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 22.16+.

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

openclaw onboard --install-daemon

openclaw gateway --port 18789 --verbose

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

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

Upgrading? Updating guide (and run openclaw doctor).

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.

From source (development)

Prefer pnpm for builds from source. Bun is optional for running TypeScript directly.

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

pnpm install
pnpm ui:build # auto-installs UI deps on first run
pnpm build

pnpm openclaw onboard --install-daemon

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

Note: pnpm openclaw ... runs TypeScript directly (via tsx). pnpm build produces dist/ for running via Node / the packaged openclaw binary.

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, BlueBubbles (iMessage), iMessage (legacy), IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, 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.

Star History

Star History Chart

Everything we built so far

Core platform

Channels

Apps + nodes

Tools + automation

Runtime + safety

Ops + packaging

How it works (short)

WhatsApp / Telegram / Slack / Discord / Google Chat / Signal / iMessage / BlueBubbles / IRC / Microsoft Teams / Matrix / Feishu / LINE / Mattermost / Nextcloud Talk / Nostr / Synology Chat / Tlon / Twitch / Zalo / Zalo Personal / WeChat / WebChat
               │
               ▼
┌───────────────────────────────┐
│            Gateway            │
│       (control plane)         │
│     ws://127.0.0.1:18789      │
└──────────────┬────────────────┘
               │
               ├─ Pi agent (RPC)
               ├─ CLI (openclaw …)
               ├─ WebChat UI
               ├─ macOS app
               └─ iOS / Android nodes

Key subsystems

Tailscale access (Gateway dashboard)

OpenClaw can auto-configure Tailscale Serve (tailnet-only) or Funnel (public) while the Gateway stays bound to loopback. Configure gateway.tailscale.mode:

  • off: no Tailscale automation (default).
  • serve: tailnet-only HTTPS via tailscale serve (uses Tailscale identity headers by default).
  • funnel: public HTTPS via tailscale funnel (requires shared password auth).

Notes:

  • gateway.bind must stay loopback when Serve/Funnel is enabled (OpenClaw enforces this).
  • Serve can be forced to require a password by setting gateway.auth.mode: "password" or gateway.auth.allowTailscale: false.
  • Funnel refuses to start unless gateway.auth.mode: "password" is set.
  • Optional: gateway.tailscale.resetOnExit to undo Serve/Funnel on shutdown.

Details: Tailscale guide · Web surfaces

Remote Gateway (Linux is great)

It’s perfectly fine to run the Gateway on a small Linux instance. Clients (macOS app, CLI, WebChat) can connect over Tailscale Serve/Funnel or SSH tunnels, and you can still pair device nodes (macOS/iOS/Android) to execute device‑local actions when needed.

  • Gateway host runs the exec tool and channel connections by default.
  • Device nodes run device‑local actions (system.run, camera, screen recording, notifications) via node.invoke. In short: exec runs where the Gateway lives; device actions run where the device lives.

Details: Remote access · Nodes · Security

macOS permissions via the Gateway protocol

The macOS app can run in node mode and advertises its capabilities + permission map over the Gateway WebSocket (node.list / node.describe). Clients can then execute local actions via node.invoke:

  • system.run runs a local command and returns stdout/stderr/exit code; set needsScreenRecording: true to require screen-recording permission (otherwise you’ll get PERMISSION_MISSING).
  • system.notify posts a user notification and fails if notifications are denied.
  • canvas.*, camera.*, screen.record, and location.get are also routed via node.invoke and follow TCC permission status.

Elevated bash (host permissions) is separate from macOS TCC:

  • Use /elevated on|off to toggle per‑session elevated access when enabled + allowlisted.
  • Gateway persists the per‑session toggle via sessions.patch (WS method) alongside thinkingLevel, verboseLevel, model, sendPolicy, and groupActivation.

Details: Nodes · macOS app · Gateway protocol

Agent to Agent (sessions_* tools)

  • Use these to coordinate work across sessions without jumping between chat surfaces.
  • sessions_list — discover active sessions (agents) and their metadata.
  • sessions_history — fetch transcript logs for a session.
  • sessions_send — message another session; optional reply‑back ping‑pong + announce step (REPLY_SKIP, ANNOUNCE_SKIP).

Details: Session tools

Skills registry (ClawHub)

ClawHub is a minimal skill registry. With ClawHub enabled, the agent can search for skills automatically and pull in new ones as needed.

ClawHub

Chat commands

Send these in WhatsApp/Telegram/Slack/Google Chat/Microsoft Teams/WebChat (group commands are owner-only):

  • /status — compact session status (model + tokens, cost when available)
  • /new or /reset — reset the session
  • /compact — compact session context (summary)
  • /think <level> — off|minimal|low|medium|high|xhigh (GPT-5.2 + Codex models only)
  • /verbose on|off
  • /usage off|tokens|full — per-response usage footer
  • /restart — restart the gateway (owner-only in groups)
  • /activation mention|always — group activation toggle (groups only)

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.

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: "anthropic/claude-opus-4-6",
  },
}

Full configuration reference (all keys + examples).

Security model (important)

  • Default: tools run on the host for the main session, so the agent has full access when it’s just you.
  • Group/channel safety: set agents.defaults.sandbox.mode: "non-main" to run non‑main sessions (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
  • Sandbox defaults: allowlist bash, process, read, write, edit, sessions_list, sessions_history, sessions_send, sessions_spawn; denylist browser, canvas, nodes, cron, discord, gateway.

Details: Security guide · Docker + sandboxing · Sandbox config

WhatsApp

  • Link the device: pnpm openclaw channels login (stores creds in ~/.openclaw/credentials).
  • Allowlist who can talk to the assistant via channels.whatsapp.allowFrom.
  • If channels.whatsapp.groups is set, it becomes a group allowlist; include "*" to allow all.

Telegram

  • Set TELEGRAM_BOT_TOKEN or channels.telegram.botToken (env wins).
  • Optional: set channels.telegram.groups (with channels.telegram.groups."*".requireMention); when set, it is a group allowlist (include "*" to allow all). Also channels.telegram.allowFrom or channels.telegram.webhookUrl + channels.telegram.webhookSecret as needed.
{
  channels: {
    telegram: {
      botToken: "123456:ABCDEF",
    },
  },
}

Slack

  • Set SLACK_BOT_TOKEN + SLACK_APP_TOKEN (or channels.slack.botToken + channels.slack.appToken).

Discord

  • Set DISCORD_BOT_TOKEN or channels.discord.token.
  • Optional: set commands.native, commands.text, or commands.useAccessGroups, plus channels.discord.allowFrom, channels.discord.guilds, or channels.discord.mediaMaxMb as needed.
{
  channels: {
    discord: {
      token: "1234abcd",
    },
  },
}

Signal

  • Requires signal-cli and a channels.signal config section.

BlueBubbles (iMessage)

  • Recommended iMessage integration.
  • Configure channels.bluebubbles.serverUrl + channels.bluebubbles.password and a webhook (channels.bluebubbles.webhookPath).
  • The BlueBubbles server runs on macOS; the Gateway can run on macOS or elsewhere.

iMessage (legacy)

  • Legacy macOS-only integration via imsg (Messages must be signed in).
  • If channels.imessage.groups is set, it becomes a group allowlist; include "*" to allow all.

Microsoft Teams

  • Configure a Teams app + Bot Framework, then add a msteams config section.
  • Allowlist who can talk via msteams.allowFrom; group access via msteams.groupAllowFrom or msteams.groupPolicy: "open".

WeChat

  • Official Tencent plugin via @tencent-weixin/openclaw-weixin (iLink Bot API). Private chats only; v2.x requires OpenClaw >=2026.3.22.
  • Install: openclaw plugins install "@tencent-weixin/openclaw-weixin", then openclaw channels login --channel openclaw-weixin to scan the QR code.
  • Requires the WeChat ClawBot plugin (WeChat > Me > Settings > Plugins); gradual rollout by Tencent.

WebChat

  • Uses the Gateway WebSocket; no separate WebChat port/config.

Browser control (optional):

{
  browser: {
    enabled: true,
    color: "#FF4500",
  },
}

Docs

Use these when you’re past the onboarding flow and want the deeper reference.

Advanced docs (discovery + control)

Operations & troubleshooting

Deep dives

Workspace & skills

Platform internals

Email hooks (Gmail)

Molty

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