Skip to main content
HowOpenClaw

System Requirements

What you need to run OpenClaw. Supported operating systems, Node.js versions, hardware requirements, and Docker support.

Minimum requirements

ComponentMinimumRecommended
Node.js22.1424 LTS
RAM512MB1GB+
Disk200MB500MB+ (for logs and memory files)
OSmacOS 12+, Ubuntu 20.04+, Windows 10+Any modern 64-bit OS

Supported operating systems

macOS

  • macOS 12 Monterey or later
  • All channels supported including iMessage
  • ARM (Apple Silicon M1/M2/M3) and Intel supported

Linux

  • Ubuntu 20.04 LTS or later
  • Debian 11+
  • Any modern 64-bit distro with Node.js 22+
  • All channels supported except iMessage

Windows

  • Windows 10 or Windows 11
  • WSL2 is supported and recommended for the best experience
  • All channels supported except iMessage
  • iMessage requires macOS on the machine running the gateway

Raspberry Pi

  • Raspberry Pi 4 (2GB RAM) recommended
  • Pi 3 works but is slow; Pi Zero is not recommended
  • Use a 64-bit OS (Raspberry Pi OS Bookworm 64-bit or Ubuntu 22.04)
  • All channels supported except iMessage

Node.js

OpenClaw requires Node.js 22.14 or later. Node.js 24 LTS is recommended.

Check your version:

node --version

Install or upgrade via nvm:

nvm install 24
nvm use 24

Or download from nodejs.org.

Why 22.14+? As of v2026.3.24, OpenClaw uses native Node.js APIs that require 22.14. Earlier versions will fail at startup with a clear error message.


Docker

OpenClaw runs in Docker. The Gateway, all channels (except iMessage), and automations work inside a container.

docker pull openclaw/openclaw:latest
docker run -d \
  -v ~/.openclaw:/root/.openclaw \
  -p 3000:3000 \
  openclaw/openclaw:latest

iMessage in Docker: Not supported. iMessage uses the macOS Messages framework, which isn't available in Linux containers.


What keeps running 24/7

For automations (cron jobs, scheduled briefings) to fire at the scheduled time, the Gateway must be running. This means the machine must:

  • Be powered on
  • Not be in sleep mode
  • Have network access (for AI provider API calls)

A Raspberry Pi or cheap VPS ($5/month) works well for always-on deployment. For personal use where you just want to respond to messages, a laptop is fine — automations simply won't fire when it's sleeping.

See Module 6: Autonomous Tasks for deployment options.


Checking your setup

Run the built-in diagnostics after installation:

openclaw doctor

This checks Node.js version, config validity, AI provider connectivity, and channel status.