Getting OpenClaw onto your machine

We have all been there—spending an entire afternoon trying to get a new tool running, only to get stuck on missing dependencies or broken environment paths. I prefer tools that get out of the way so I can actually start building. If you want to get OpenClaw up and running without the headache, this guide covers the fastest paths to a working setup.

What You’ll Need

Before we start, make sure your environment meets these requirements:

• Node 22+ (The installer script can handle this for you)
• macOS, Linux, or Windows (I suggest using WSL2 if you are on Windows)
• pnpm (Only required if you plan to build from source)

Quick Start

The fastest way to get started is the installer script. I recommend this method because it handles Node detection, installation, and the onboarding wizard in one go.

1. Run the installer

Open your terminal and run the command for your system:

macOS / Linux / WSL2

curl -fsSL https://openclaw.ai/install.sh | bash

Windows (PowerShell)

iwr -useb https://openclaw.ai/install.ps1 | iex

2. Skip onboarding (Optional)

If you want to install the binary without the wizard, use these flags:

macOS / Linux / WSL2

curl -fsSL https://openclaw.ai/install.sh | bash -s -- --no-onboard

Windows (PowerShell)

& ([scriptblock]::Create((iwr -useb https://openclaw.ai/install.ps1))) -NoOnboard

3. Verify the setup

Once the script finishes, I usually run these commands to make sure everything is healthy:

openclaw doctor         # checks for config issues
openclaw status         # checks the gateway status
openclaw dashboard      # opens the UI in your browser

Alternative Install Methods

If you prefer to manage your own packages, you can use npm or pnpm.

Using npm

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

Using pnpm

pnpm requires you to approve build scripts for certain dependencies:

pnpm add -g openclaw@latest
pnpm approve-builds -g
openclaw onboard --install-daemon

From Source

If you want to contribute or run a local checkout, follow these steps:

1. Clone and build:

   git clone https://github.com/openclaw/openclaw.git
   cd openclaw
   pnpm install
   pnpm ui:build
   pnpm build

2. Link the CLI:

   pnpm link --global

3. Onboard:

   openclaw onboard --install-daemon

Troubleshooting

openclaw not found

If your terminal says the command isn’t found, your shell likely cannot see global npm binaries. Run these to diagnose:

node -v
npm prefix -g
echo "$PATH"

If the output of npm prefix -g is not in your $PATH, add it to your ~/.zshrc or ~/.bashrc:

export PATH="$(npm prefix -g)/bin:$PATH"

sharp build errors

If you see errors related to sharp or libvips on macOS, try forcing prebuilt binaries:

SHARP_IGNORE_GLOBAL_LIBVIPS=1 npm install -g openclaw@latest

What’s Next

Now that you are set up, you might want to look into these specific deployment options:

• Docker Installation
• Nix Setup
• Ansible Provisioning
• Bun Runtime Usage

If you hit a wall during setup, check out the AI Setup Assistant.