OpenClaw System Requirements: Hardware & Software Guide

Quick Answer: OpenClaw requires minimum 4 CPU threads, 2GB RAM (4GB recommended), and Node.js 22+. It runs natively on macOS and Linux; Windows users need WSL2. Storage footprint is under 500MB. You also need an API key from at least one LLM provider (Anthropic, OpenAI, Google, or local via Ollama).

OpenClaw is lightweight by design. With 200,000+ GitHub stars and an MIT license, it is built to run on everything from a Raspberry Pi to a dedicated VPS — no expensive hardware required.

What Are the Minimum and Recommended Specs?

OpenClaw is surprisingly lightweight. Here is what you need to run it effectively.

ComponentMinimumRecommended
CPU4 threads (x86_64 or ARM64)8+ threads
RAM2GB4GB (8-16GB for local LLMs)
Storage500MB free2GB+ (more for local models)
Node.jsv22+v22 LTS (latest)
NetworkBroadband internetLow-latency connection for API calls

Which Operating Systems Does OpenClaw Support?

OpenClaw supports macOS and Linux natively. Windows requires WSL2.

macOS

Native support12 Monterey or newer

Best developer experience. Install via Homebrew or direct download.

Linux

Native supportUbuntu 22.04+, Debian 12+, Fedora 38+

First-class support. Works on most modern distributions with Node.js 22.

Windows

Via WSL2 onlyWindows 10/11 with WSL2

Requires WSL2 installation first. Native Windows is not supported.

Raspberry Pi OS

SupportedBookworm (64-bit)

Pi 4 (4GB+) or Pi 5 required. Must use 64-bit OS for Node.js 22.

ChromeOS

Community supportedWith Linux (Crostini) enabled

Enable Linux development environment in ChromeOS settings, then follow Linux instructions.

What LLM Providers Does OpenClaw Support?

OpenClaw is model-agnostic. Connect to any of these providers or run models locally.

Anthropic (Claude)

Claude 3.5 Sonnet, Claude 3 Opus. Excellent for complex reasoning and coding tasks.

$3-15 per million tokens

OpenAI (GPT-4o)

GPT-4o, GPT-4o-mini. Strong general-purpose performance with fast response times.

$2.50-10 per million tokens

Google (Gemini)

Gemini 2.0, Gemini 1.5 Pro. Good multimodal capabilities and long context windows.

$1.25-5 per million tokens

DeepSeek

DeepSeek V3, DeepSeek Coder. Budget-friendly with strong coding abilities.

$0.27-1.10 per million tokens

Kimi K2.5

Kimi K2.5 from Moonshot AI. Competitive pricing with solid performance.

Varies by plan

Ollama (Local)

Run Llama, Mistral, Phi, or other open models locally. Zero API costs, full privacy.

Free (hardware costs only)

What Are the Best VPS Options for OpenClaw?

If you want OpenClaw running 24/7 without keeping your computer on, a VPS costs $5-15 per month.

ProviderPlanSpecsCost
DigitalOceanBasic Droplet2 vCPU, 4GB RAM, 80GB SSD$12/month
HetznerCX222 vCPU, 4GB RAM, 40GB SSD$5/month
VultrCloud Compute2 vCPU, 4GB RAM, 80GB SSD$12/month
LinodeShared 4GB2 vCPU, 4GB RAM, 80GB SSD$12/month
AWS Lightsail4GB Instance2 vCPU, 4GB RAM, 80GB SSD$15/month

Raspberry Pi Compatibility

OpenClaw runs on Raspberry Pi 4 (4GB+ model) and Raspberry Pi 5. The ARM64 architecture is supported by Node.js 22, and the Pi's low power consumption (5-15W) makes it ideal for an always-on AI agent that costs pennies per day in electricity.

  • Raspberry Pi 4 with 4GB RAM: adequate for API-based LLM usage
  • Raspberry Pi 5 with 8GB RAM: recommended for best performance
  • Must use 64-bit Raspberry Pi OS (Bookworm) for Node.js 22 support
  • Local LLM inference is limited — use API providers for best results on Pi
  • Total hardware cost: under $50 for a complete always-on setup

See our full guide: OpenClaw on Raspberry Pi

Frequently Asked Questions

Stop Wasting 40-60% of Your AI Budget

Download the free '6 Token Drains' guide — identify the hidden patterns burning through your tokens and get copy-paste fixes for each one.

Read the Free Guide
See what we've built for real businesses →

Your Competitors Are Already Automating. Are You?

Every week we send one automation that saves 10+ hours of manual work — the same playbooks our clients use to run their businesses on autopilot. Miss a week, miss the edge.

Save 10+ hours/week Cut AI costs by 97% Deploy in under 20 min

Get the Automation Playbook (Free)

One deploy-ready automation every week. Same strategies our clients pay thousands for. 400+ business owners already inside.

Need it done for you?

Book a Free Strategy Call See what we've built for real businesses →