Blog

OpenClaw runs on Windows 11. Here is everything you need to get started.

Step 1: Install Node.js

Download the LTS version from nodejs.org and install with default settings. Verify: open Command Prompt and type node --version.

Step 2: Install OpenClaw

Open Command Prompt as Administrator:

npm install -g openclaw

Step 3: Setup and Start

openclaw setup
openclaw start

Follow the prompts to connect your Telegram or other messaging channel.

Run on Startup

Press Win+R, type shell:startup, create a file called openclaw.bat with the line openclaw start. OpenClaw will start with Windows automatically.

Windows vs VPS

Running on Windows works well if your PC stays on. For always-on availability without your PC running, a DigitalOcean VPS at $6/month (with $200 free credit) is the better choice.

Both DigitalOcean and Vultr run OpenClaw excellently. Here is an honest comparison.

Quick Verdict

• Best for beginners: DigitalOcean — cleaner UI, better docs
• Best value / global coverage: Vultr — 32 locations, competitive pricing

Pricing

Both start at ~$6/month for 2GB RAM. Vultr’s High Frequency instances offer better CPU per dollar.

Ease of Use

DigitalOcean wins here. The dashboard is the cleanest in the industry. Perfect for first-time VPS users.

Welcome Credits

DigitalOcean: $200 free credit. Vultr: up to $250 during promotions.

Our Pick

Start with DigitalOcean if you are new to VPS hosting. The documentation and $200 credit make it the easiest entry point.

Get started with DigitalOcean ($200 free) →

For maximum global coverage: Try Vultr →

DigitalOcean is the fastest way to get OpenClaw running in the cloud. New users get $200 in free credits — enough for 2+ years at the entry tier.

Step 1: Create Your Account

Sign up at DigitalOcean and claim your $200 credit.

Step 2: Create a Droplet

Click Create → Droplets. Choose Ubuntu 22.04 LTS, Basic plan at $6/month (2GB RAM), and your nearest datacenter.

Step 3: Connect via SSH

ssh root@YOUR_IP

Step 4: Install Node.js

curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejs

Step 5: Install OpenClaw

npm install -g openclaw
openclaw setup
openclaw start

Step 6: Keep It Running 24/7

npm install -g pm2
pm2 start openclaw --name openclaw
pm2 startup && pm2 save

Your OpenClaw is now live 24/7. Get your $200 DigitalOcean credit →

RAM is one of the most common questions when setting up OpenClaw. The answer depends on how you use it — but here’s a clear breakdown for every scenario.

Minimum RAM Requirements

OpenClaw itself (the Node.js process) uses approximately 200-400MB of RAM at idle. That’s very lean. The minimum to run OpenClaw is technically 512MB, but 1GB gives comfortable headroom.

Practical RAM Recommendations

Basic Use (Cloud AI Models Only)

If you’re using OpenClaw with cloud-based AI models — Claude, GPT-4, Gemini — and not running anything locally, 2GB RAM is plenty. This covers:

• OpenClaw process (~300MB)
• Operating system overhead (~500MB on Linux)
• Headroom for browser automation and file operations

Standard Use (Most People)

4GB RAM is the sweet spot for most OpenClaw users. This gives you room to run OpenClaw, keep several browser tabs open for automation tasks, and handle multiple simultaneous operations without slowdown.

Power Use (Local AI Models)

If you want to run local AI models via Ollama alongside OpenClaw, you need significantly more RAM:

• Llama 3.2 3B model: ~4GB RAM
• Llama 3.1 8B model: ~8GB RAM
• Mistral 7B: ~8GB RAM
• Llama 3.1 70B: ~40GB+ RAM (requires high-end hardware)

For this setup, get at least 16GB RAM so both OpenClaw and the local model have breathing room.

RAM by Platform

• VPS (DigitalOcean/Vultr): $6/month Basic Droplet (2GB) works fine for cloud models. Get $200 free credit →
• Mac Mini: 8GB base model works, 16GB recommended
• Raspberry Pi 5: Get the 4GB or 8GB model
• Windows/Linux PC: Any modern machine with 8GB+ RAM is fine

Bottom Line

For most people using OpenClaw with cloud AI: 2-4GB RAM is all you need. If you want to experiment with running local models: 16GB+. Don’t over-spec your hardware just for OpenClaw — it’s designed to be efficient.

The Raspberry Pi is the most affordable way to run OpenClaw 24/7 at home. A Pi 5 sitting on your desk uses about 5W of power and can keep your AI agent running constantly for pennies a month. Here’s what you need to know.

Recommended: Raspberry Pi 5 (4GB or 8GB)

The Pi 5 is 2-3x faster than the Pi 4 and handles Node.js workloads (which OpenClaw runs on) much better. Get the 4GB model minimum — 8GB is better if your budget allows.

Raspberry Pi 5 on Amazon →

Can You Use Raspberry Pi 4?

Yes, but it’s slower. OpenClaw will run on a Pi 4 with 4GB RAM, but response times will be noticeably slower than a Pi 5, especially for tasks that involve lots of file I/O or simultaneous operations. If you already have a Pi 4, it’s worth trying — if you’re buying new, get the Pi 5.

What You’ll Need

• Raspberry Pi 5 (4GB or 8GB) — Amazon
• MicroSD card (32GB+ Class 10) or NVMe SSD via PCIe hat for better performance
• Official Pi 5 power supply (27W USB-C)
• Case with active cooling recommended

Pi vs VPS: Which Should You Choose?

Choose a Raspberry Pi if you want local control, don’t mind the one-time hardware cost (~$80-120), and have a reliable internet connection at home.

Choose a VPS if you want zero maintenance, guaranteed uptime, and remote access even when your home internet is down. DigitalOcean starts at $6/month with $200 free credit for new users.

Setting Up OpenClaw on Raspberry Pi

Flash Raspberry Pi OS (64-bit) to your SD card, install Node.js 20+, and follow the standard OpenClaw Linux installation. Set it up as a systemd service so it starts automatically on boot and restarts if it crashes.

The Mac Mini is one of the best home servers for running OpenClaw. It’s quiet, power-efficient, runs macOS natively (where OpenClaw is fully supported), and sits unobtrusively on any desk. Here’s which model to get.

TL;DR Recommendation

Get the Mac Mini M4 (16GB RAM). It’s the sweet spot of price, performance, and longevity for running OpenClaw as a 24/7 home server.

Check Mac Mini M4 price on Amazon →

Mac Mini M4 (2024) — Best Choice

The M4 chip is significantly faster than M2 and M3 for AI workloads. With 16GB unified memory, you can run OpenClaw alongside local AI models (like Ollama) without hitting memory limits. The base $599 model comes with 8GB which works, but 16GB gives you much more headroom.

Mac Mini M2 (2023) — Best Budget Pick

Still an excellent machine for OpenClaw. Available refurbished starting around $399, the M2 handles OpenClaw without any issues. If budget is a constraint, this is the smart buy — it will run OpenClaw flawlessly for years.

Find Mac Mini M2 deals on Amazon →

Mac Mini M4 Pro — Overkill for Most Users

Unless you’re running multiple AI models simultaneously or doing heavy local inference, the M4 Pro is more than you need for OpenClaw. The base M4 handles everything OpenClaw does with ease.

How Much RAM Do You Need?

• 8GB — Sufficient for OpenClaw with cloud-based AI models (Claude, GPT, Gemini)
• 16GB — Recommended if you want to run local models with Ollama alongside OpenClaw
• 24GB+ — Only needed if running large local models (70B parameter models etc.)

Setting Up OpenClaw on Mac Mini

Mac Mini with macOS is one of the easiest OpenClaw setups. Install Node.js via Homebrew, run the OpenClaw installer, and configure it to start on login. Full guide: How to Install OpenClaw on Mac Mini.

Running OpenClaw on a VPS means your AI agent is available 24/7, accessible from any device, and doesn’t drain your laptop battery. Here are the best VPS options for OpenClaw in 2026, ranked by value, reliability, and ease of setup.

What to Look for in an OpenClaw VPS

• RAM: At least 2GB for basic use, 4GB+ recommended for running AI models locally
• CPU: 2+ vCPUs for smooth performance
• Storage: 25GB SSD minimum
• OS: Ubuntu 22.04 LTS or Debian 12 work best
• Location: Choose a region close to you for lower latency

1. DigitalOcean — Best Overall

DigitalOcean is the go-to choice for running OpenClaw. Their Droplets are easy to set up, the control panel is beginner-friendly, and performance is consistently solid. The $6/month Basic Droplet (2GB RAM, 1 vCPU, 50GB SSD) handles OpenClaw comfortably.

New users get $200 in free credits — that’s over 2 years of hosting at the entry tier.

Get started with DigitalOcean ($200 free credit) →

2. Vultr — Best for Flexibility

Vultr offers similar specs to DigitalOcean at competitive prices, with 32 global data center locations — the widest coverage of any provider on this list. Their High Frequency instances are particularly fast for compute-heavy tasks.

Try Vultr →

3. Hetzner — Best Value in Europe

If you’re based in Europe, Hetzner offers incredible value — their CAX11 ARM instance (4GB RAM, 2 vCPUs) costs around €3.79/month. Excellent performance per euro, though US-based servers have slightly higher latency from North America.

4. Linode (Akamai) — Most Established

Linode has been around since 2003 and is known for reliability. Their Nanode plan starts at $5/month with 1GB RAM — fine for lightweight OpenClaw use, but upgrade to the $10/month plan for more headroom.

Recommended Setup

For most users starting out, a DigitalOcean Basic Droplet at $6-12/month is the right call. Create an Ubuntu 22.04 droplet, install Node.js, and follow the OpenClaw setup guide on this site. With the $200 credit, you won’t pay anything for months.

Claim your $200 DigitalOcean credit →

One of the most powerful features of OpenClaw is its Skills system. Skills are modular extensions that give your OpenClaw agent new capabilities — from checking the weather to running full coding sessions. If you want to get more out of OpenClaw, understanding skills is essential.

What Are OpenClaw Skills?

Skills are self-contained capability packages that you install into OpenClaw. Each skill comes with its own SKILL.md file that tells the agent exactly how and when to use it. When a task matches a skill’s description, OpenClaw automatically loads and follows the skill’s instructions.

Think of skills like apps on your phone — OpenClaw is the operating system, and skills extend what it can do without modifying the core.

How to Install OpenClaw Skills

Skills live in your OpenClaw installation directory. To install a skill:

1. Download the skill package (usually a folder with a SKILL.md and any supporting files)
2. Place it in your OpenClaw skills directory
3. OpenClaw automatically discovers and loads it on next startup

You can also find community skills on ClawhHub.com — the official skill marketplace.

Built-In Skills That Come With OpenClaw

Coding Agent

Delegates complex coding tasks to Codex, Claude Code, or Pi agents running in the background. Perfect for building new features, reviewing PRs, or refactoring large codebases without blocking your main session.

Weather

Gets current weather and forecasts via wttr.in or Open-Meteo. No API key needed. Just ask “what’s the weather in New York?” and OpenClaw handles it.

Healthcheck

Security hardening and risk-tolerance configuration for OpenClaw deployments. Runs firewall checks, SSH hardening, update status, and more — useful for VPS deployments especially.

MCP Porter

Connects OpenClaw to MCP (Model Context Protocol) servers and tools. Lets you list, configure, and call external services directly from your agent.

Node Connect

Diagnoses OpenClaw node connection and pairing failures. Essential for multi-device setups running OpenClaw across Android, iOS, and macOS.

Skill Creator

Meta-skill that helps you create new skills. Describe what you want the skill to do and it builds the SKILL.md for you.

How OpenClaw Chooses Which Skill to Use

Before responding to any request, OpenClaw scans the descriptions of all installed skills. If one clearly matches the task, it reads that skill’s instructions and follows them. If multiple could apply, it picks the most specific one.

This means skill selection is automatic — you don’t need to explicitly activate a skill. Just ask OpenClaw to do something and it figures out if a skill applies.

Creating Your Own Skills

Custom skills are just folders with a SKILL.md file. The file contains:

• A name and description (what triggers the skill)
• A location (path to the skill folder)
• Instructions for the agent (what to do when triggered)
• Any supporting scripts or reference files

You can create skills for anything repetitive — generating reports, checking APIs, managing files, posting to social media. If you can describe the process in plain language, you can turn it into a skill.

Running Skills 24/7

To get the most value from skills, OpenClaw needs to run continuously. This is where your hardware choice matters. A DigitalOcean droplet (starting at $4/month — new users get $200 credit) is the easiest way to keep OpenClaw running around the clock, with all your skills available at any time.

For local hosting, a Mac Mini or Raspberry Pi 5 running OpenClaw as a background service works well too.

Where to Find More Skills

• ClawhHub.com — official skill marketplace
• The OpenClaw Discord — community-built skills
• GitHub — search “OpenClaw skill”

Skills are what turn OpenClaw from a chat assistant into a genuine autonomous agent. The more skills you install, the more tasks OpenClaw can handle without you. That’s the goal.

Running OpenClaw on a VPS means your AI agent is available 24/7, accessible from any device, and doesn’t drain your laptop battery. Here are the best VPS options for OpenClaw in 2026, ranked by value, reliability, and ease of setup.

What to Look for in an OpenClaw VPS

• RAM: At least 2GB for basic use, 4GB+ recommended for running AI models locally
• CPU: 2+ vCPUs for smooth performance
• Storage: 25GB SSD minimum
• OS: Ubuntu 22.04 LTS or Debian 12 work best
• Location: Choose a region close to you for lower latency

1. DigitalOcean — Best Overall

DigitalOcean is the go-to choice for running OpenClaw. Their Droplets are easy to set up, the control panel is beginner-friendly, and performance is consistently solid. The $6/month Basic Droplet (2GB RAM, 1 vCPU, 50GB SSD) handles OpenClaw comfortably.

New users get $200 in free credits — that’s over 2 years of hosting at the entry tier.

Get started with DigitalOcean ($200 free credit) →

2. Vultr — Best for Flexibility

Vultr offers similar specs to DigitalOcean at competitive prices, with 32 global data center locations — the widest coverage of any provider on this list. Their High Frequency instances are particularly fast for compute-heavy tasks.

Try Vultr →

3. Hetzner — Best Value in Europe

If you’re based in Europe, Hetzner offers incredible value — their CAX11 ARM instance (4GB RAM, 2 vCPUs) costs around €3.79/month. Excellent performance per euro, though US-based servers have slightly higher latency from North America.

4. Linode (Akamai) — Most Established

Linode has been around since 2003 and is known for reliability. Their Nanode plan starts at $5/month with 1GB RAM — fine for lightweight OpenClaw use, but upgrade to the $10/month plan for more headroom.

Recommended Setup

For most users starting out, a DigitalOcean Basic Droplet at $6-12/month is the right call. Create an Ubuntu 22.04 droplet, install Node.js, and follow the OpenClaw setup guide on this site. With the $200 credit, you won’t pay anything for months.

Claim your $200 DigitalOcean credit →

One of the most powerful features of OpenClaw is its Skills system. Skills are modular extensions that give your OpenClaw agent new capabilities — from checking the weather to running full coding sessions. If you want to get more out of OpenClaw, understanding skills is essential.

What Are OpenClaw Skills?

Skills are self-contained capability packages that you install into OpenClaw. Each skill comes with its own SKILL.md file that tells the agent exactly how and when to use it. When a task matches a skill’s description, OpenClaw automatically loads and follows the skill’s instructions.

Think of skills like apps on your phone — OpenClaw is the operating system, and skills extend what it can do without modifying the core.

How to Install OpenClaw Skills

Skills live in your OpenClaw installation directory. To install a skill:

1. Download the skill package (usually a folder with a SKILL.md and any supporting files)
2. Place it in your OpenClaw skills directory
3. OpenClaw automatically discovers and loads it on next startup

You can also find community skills on ClawhHub.com — the official skill marketplace.

Built-In Skills That Come With OpenClaw

Coding Agent

Delegates complex coding tasks to Codex, Claude Code, or Pi agents running in the background. Perfect for building new features, reviewing PRs, or refactoring large codebases without blocking your main session.

Weather

Gets current weather and forecasts via wttr.in or Open-Meteo. No API key needed. Just ask “what’s the weather in New York?” and OpenClaw handles it.

Healthcheck

Security hardening and risk-tolerance configuration for OpenClaw deployments. Runs firewall checks, SSH hardening, update status, and more — useful for VPS deployments especially.

MCP Porter

Connects OpenClaw to MCP (Model Context Protocol) servers and tools. Lets you list, configure, and call external services directly from your agent.

Node Connect

Diagnoses OpenClaw node connection and pairing failures. Essential for multi-device setups running OpenClaw across Android, iOS, and macOS.

Skill Creator

Meta-skill that helps you create new skills. Describe what you want the skill to do and it builds the SKILL.md for you.

How OpenClaw Chooses Which Skill to Use

Before responding to any request, OpenClaw scans the descriptions of all installed skills. If one clearly matches the task, it reads that skill’s instructions and follows them. If multiple could apply, it picks the most specific one.

This means skill selection is automatic — you don’t need to explicitly activate a skill. Just ask OpenClaw to do something and it figures out if a skill applies.

Creating Your Own Skills

Custom skills are just folders with a SKILL.md file. The file contains:

• A name and description (what triggers the skill)
• A location (path to the skill folder)
• Instructions for the agent (what to do when triggered)
• Any supporting scripts or reference files

You can create skills for anything repetitive — generating reports, checking APIs, managing files, posting to social media. If you can describe the process in plain language, you can turn it into a skill.

Running Skills 24/7

To get the most value from skills, OpenClaw needs to run continuously. This is where your hardware choice matters. A DigitalOcean droplet (starting at $4/month — new users get $200 credit) is the easiest way to keep OpenClaw running around the clock, with all your skills available at any time.

For local hosting, a Mac Mini or Raspberry Pi 5 running OpenClaw as a background service works well too.

Where to Find More Skills

• ClawhHub.com — official skill marketplace
• The OpenClaw Discord — community-built skills
• GitHub — search “OpenClaw skill”

Skills are what turn OpenClaw from a chat assistant into a genuine autonomous agent. The more skills you install, the more tasks OpenClaw can handle without you. That’s the goal.