Lesson 4 · OpenClaw, Safely Pro ~12 min read Hands-on install

Install and onboard, step by step.

You did the Lesson 3 prep: an isolated machine, a dedicated API key with a spend cap, a kill-switch plan. Now the fun part — from bare machine to an agent that answers you, in about 25 minutes. We follow the official openclaw onboard wizard, with the two safety verifications most guides skip entirely.

OpenClaw ships new releases weekly, so menus and wording drift. This lesson teaches the decisions, which are stable — when a screen looks different, the choice behind it is still the one described here. Where exact commands matter, cross-check the official docs at docs.openclaw.ai. (Independent reality: we update this lesson with each significant change — that's the point of us.)

01 Prerequisites (5 minutes)

On your prepared machine you need exactly three things:

Verify Node firstnode --version # Want: v22.x or newer. If "command not found," install Node before continuing.

02 Run the onboarding wizard

1

Start the wizard

Terminalnpm install -g openclaw@latest openclaw onboard

The wizard walks you through gateway, workspace, channels, and skills. You'll make four decisions — here's the safe answer to each.

2

Decision: quickstart or custom? → Custom

Quickstart optimizes for the demo high. Custom takes three extra minutes and lets you make the binding choice deliberately — which is the one choice that matters.

3

Decision: where to bind the gateway? → Localhost. Always localhost.

This is THE setting from Lesson 3. When asked where the gateway should listen, choose 127.0.0.1 (localhost) — never 0.0.0.0, never your machine's LAN address "just to test." Remote access comes via Tailscale later, not via an open door now.

4

Decision: model provider → the brain you budgeted for

Paste your dedicated API key when asked. Model guidance, honestly: a mid-tier model is the right starting brain (Claude Sonnet-class or equivalent) — smart enough for real work, cheap enough that an always-on agent doesn't sting. Save frontier models for when a specific task proves it needs one. You can change this anytime; your spend cap has your back while you learn the cost rhythm.

5

Decision: run as a service? → Yes

Let the wizard install OpenClaw as a system service (systemd on Linux, launchd on macOS) so it survives reboots. Bonus: this also teaches you half your kill switch —

Your stop/start commands (sticky note!)# Linux sudo systemctl stop openclaw # stop NOW sudo systemctl start openclaw # resume # macOS: use the wizard-provided launchctl equivalents
6

Skip skills and extra channels — for now

The wizard will offer to connect chat apps and install skills. Decline both today. Channels are Lesson 5 (done carefully), skills are Lesson 7 (done very carefully). Today's goal is a working, private, boring agent.

03 Say hello

With the service running, open the local web chat (the wizard prints the localhost URL) and introduce yourself. Give it a small real task — "what's on this machine in the workspace folder?" or "summarize this pasted article." Confirm it thinks, answers, and feels alive. Enjoy the moment — it's a legitimately great one.

04 The two verifications nobody does (do them)

A

Verify you're not on the internet

From ANOTHER device on a DIFFERENT network (e.g., phone on cellular)# Try to reach your agent's gateway port at your home IP. # Expected result: nothing. Timeout. Dead air. # If anything answers, stop the service and revisit binding NOW.

Also worth doing: search your home's public IP on shodan.io (free) — the same scanner that finds exposed instances can confirm you're not one.

B

Verify the spend cap is real

Check your provider's usage dashboard after the first day. You should see small, explainable numbers. You're learning the agent's cost rhythm now, while it does almost nothing — so you'll notice immediately if something later makes it spike.

State achieved: a working agent, reachable only from your own machines, with a capped budget and a tested off switch.

Run it boring for 48 hours

Before connecting WhatsApp or anything exciting: just use the local chat for two days. Ask it real questions, watch the usage dashboard, stop and restart the service once for practice. Trust is built in the boring phase — and you'll meet Lesson 5 knowing exactly how your agent behaves when nothing is wrong.

What you can do now

  • Install OpenClaw via the official onboard wizard with Node 22+
  • Make the four wizard decisions safely: custom setup, localhost binding, budgeted model, run-as-service
  • Start and stop the agent on command — your kill switch is now muscle memory
  • Verify from an outside network that your gateway is unreachable
  • Read your provider's usage dashboard and recognize your agent's normal cost rhythm
  • Resist the urge to connect everything on night one
Pro
Up next in OpenClaw, Safely

Lesson 5 · Connect your channels: WhatsApp, Telegram, Discord

Your agent meets your chat apps — one channel, done right, including the shared-context trap that leaks secrets into group chats. See pricing →