How to install OpenClaw: the three commands, and what comes after

Before you start: two prerequisites

• Node.js. OpenClaw requires Node 24.16+ or 26.1+, and recommends Node 26; Node 22 and Node 25 stopped being supported in OpenClaw 2026.9.3. node --version tells you where you stand. The version requirement has its own guide, including the npm --allow-scripts wrinkle and updating Node without breaking other projects. macOS, Linux, and Windows are all supported. On Windows, the project’s own starting point is its Windows Hub desktop app, with the PowerShell installer and WSL2 as the other two routes.
• A model. OpenClaw brings the agent; the thinking is a model you connect yourself, with a provider’s API key or a Claude Code or Codex sign-in already on the machine, which onboarding can reuse. What that means and where to get one has its own guide. Create the key and set a spending cap before you start, and onboarding becomes a copy-paste.

The three commands

npm install -g openclaw@latest --allow-scripts=openclaw
openclaw onboard --install-daemon
openclaw dashboard

What each actually does:

• npm install -g openclaw@latest installs the OpenClaw CLI globally: the -g flag makes openclaw available as a command anywhere, rather than inside one project folder. --allow-scripts=openclaw lets npm 12 (and 11.16 or later) run OpenClaw’s setup scripts, which it otherwise blocks; on npm 11.15 or older, leave the flag off.
• openclaw onboard --install-daemon runs the setup wizard in its classic, step-by-step form (any setup flag opens that one): model provider and sign-in, initial preferences, and, because of the --install-daemon flag, it registers the Gateway as a background service so your agent starts with the machine and keeps running when you close the terminal.
• openclaw dashboard opens the Control UI in your browser: the web interface where you meet your agent, connect channels, and manage settings.

Prefer not to manage Node yourself? OpenClaw’s installer script (curl -fsSL https://openclaw.ai/install.sh | bash, or iwr -useb https://openclaw.ai/install.ps1 | iex in PowerShell) installs Node if it’s missing, installs OpenClaw and starts onboarding, and the project’s desktop apps for macOS, Windows and Linux install it like any other app.

From there, the natural next steps are connecting a chat channel (Telegram is the easiest first one) and saying hello.

What the installer just decided for you

Worth knowing on day one, so nothing later is a surprise:

• Everything lives in ~/.openclaw. Config, sessions, and your agent’s workspace and memory: one folder to protect and back up.
• The Gateway binds to loopback. Only your own machine can reach it, a deliberately safe default. Keep it that way; remote access has right answers that aren’t “open the port.”
• Unknown chat senders get pairing challenges, not conversations (the default pairing policy). You approve who can talk to your agent.

The decision bigger than the install

The commands above put OpenClaw on whatever machine you’re sitting at, right for a first evening. But an agent is only as available as its computer, and a laptop that sleeps takes the agent with it. Once you know you’re keeping it, the real decision is where it should permanently live: a server you run (the official docs ship Docker and VPS guides), or a managed home like Everpod’s OpenClaw pod, where the install, the security, and the always-on part arrive done. Verify anything here against the official install docs if you’re reading this long after mid-2026. OpenClaw moves fast.