YOUR PROJECT + OUR INFRASTRUCTURE
OpenClaw VPS
A VPS with OpenClaw pre-installed · By OpenClaw Foundation
Your AI, running on a server of your own.
A personal AI assistant that gets things done over WhatsApp and Telegram, installed on your VPS with HTTPS and an e-mailed sign-in link.
- AI agents, chats and flows on your own server
- You choose the models and providers to use
- More memory and CPU when the models need it
from R$59.90/mo
Pay with Pix, bank slip or card · You choose the location and the plan on the next screen. Nothing is charged until you confirm.
Ready in minutes
Automatic provisioning once the order is confirmed.
24/7 support
Our own team, by chat and ticket.
Pick the right plan for OpenClaw
Every plan includes public IPv4 and IPv6, NVMe storage and a 1 Gbps uplink. Click one to reach the checkout with everything filled in.
How to size your project
Apps that call models over an API (OpenAI, Anthropic and others) need little server; apps that run the model on the server itself need a lot of memory and, without a GPU, answer more slowly. Size the plan by model size and number of users.
- Recommended for OpenClaw
How to order OpenClaw
Pick a plan
vCPU, memory and disk sized for your project. You can grow it later without reinstalling.
Confirm the order
Pix, bank slip or card. Nothing is charged until you confirm, and you have a 7-day guarantee.
OpenClaw ready in minutes
The server comes up with OpenClaw installed and configured. Access details appear in the panel.
What to use a OpenClaw VPS for
Some of the most common uses. The server is yours — run whatever you like on it.
- AI assistants and agents on a server of your own, next to your data
- Connect the model providers you choose, or open models running on the server itself
- Support chatbots and internal knowledge bases
- Automate work with AI while keeping control of where the data lives
OpenClaw VPS specifications
- Virtualisation
- KVM, virtual server with your plan’s resources
- vCPU
- 2 to 48
- Memory
- 2 GB to 192 GB
- Storage
- NVMe, 30 GB to 2 TB
- Network
- 1 Gbps, public IPv4 and IPv6 included; DDoS protection available
- Datacenters
- Belo Horizonte (Brazil) · Dallas (USA)
- System
- OpenClaw, pre-installed
- Management
- Web panel, API and MCP, VNC console, snapshots, backups and firewall
- Billing
- Monthly, quarterly, semi-annual or annual (discounted); Pix, bank slip or card
- Support and guarantee
- 24/7, 7-day money-back guarantee
About OpenClaw
OpenClaw (formerly Clawdbot and Moltbot) is an open-source personal AI assistant that runs on your own server and talks to you over WhatsApp, Telegram, Discord and other messaging apps. What sets it apart from an ordinary chatbot is that it acts: it runs commands, reads and writes files, follows scheduled routines and learns procedures you teach it as skills.
It is for anyone who wants an assistant on their phone all day: a routine that sends a summary every morning, a reminder at the right time, a script that runs on the server and reports back on Telegram when it finishes. It also works in groups, and one gateway can keep separate agents and sessions for each person or project.
An assistant like this has to stay on: on a laptop that goes to sleep, it drops off WhatsApp. On a VPS it stays online around the clock and apart from your personal computer, which matters for an agent that runs commands. Conversations, memory and channel credentials live on a server you own; whatever you send to the AI model is processed by the provider you choose.
At Master da Web there is nothing to install: OpenClaw comes from the official image, in a container and pinned to its version, behind Caddy with HTTPS and an automatic certificate. The welcome e-mail carries the dashboard address, a secret sign-in link — open it, press Sign in and the browser is signed in as the administrator, with no token to paste — and the gateway token for OpenClaw's apps and command line. The same details are kept in /root/openclaw.txt, readable only by root. The gateway publishes no port of its own: only Caddy answers, on ports 80 and 443, and the agent's commands run inside the container.
Once signed in, you add a model provider under Settings > Models — your own API key from OpenAI, Anthropic, Google or another supported provider — and connect channels under Settings > Channels. Model usage is billed by that provider, separately from the VPS: the server runs the agent, not the model, and has no GPU. Using your own domain is optional and yours to set up.
Software features
- An AI assistant that gets things done, not just answers
- Talks over WhatsApp, Telegram, Discord and other messaging apps
- Scheduled routines, hooks and webhooks to automate your day
- Skills to teach the agent procedures it repeats
- Works with models from OpenAI, Anthropic, Google and other providers
- Web dashboard to chat, configure and follow sessions
- Official container image, pinned version, automatic HTTPS (Caddy)
- E-mailed sign-in link: admin access with no token to paste
- Every browser becomes a paired device you can remove
- By default, unknown contacts get a pairing code, not an answer
- Gateway exposes no port; agent commands run inside the container
- openclaw-update to change release; openclaw-signin-link --rotate
Requirements
Platform minimum
- Memory
- 2 GB
- Storage
- 30 GB
Below this the order is refused — the checkout raises the disk for you automatically.
Recommended for production
- vCPU
- 3 vCPU
- Memory
- 4 GB
- Storage
- 40 GB
What we would put it on, not a limit.
What your OpenClaw gets at Master da Web
Manage infrastructure from one panel: security, recovery, connectivity and growth. Check prices and availability when configuring your server.
Snapshots
Take a snapshot of OpenClaw before a risky update and roll back to it with one click, without reinstalling anything.
Automatic backups
Scheduled copies of the whole server, kept off the host. Restore the complete OpenClaw whenever you need to.
Managed firewall
Rules by port and source, applied from the panel, no iptables editing. Open only what OpenClaw needs.
Security Center
Continuous external scanning of your server, with findings prioritised and the fix spelled out for each one.
Private network (VPC)
Connect OpenClaw to databases and other servers over an isolated network with nothing exposed to the internet. With a VPN Gateway for remote access.
DDoS protection
Volumetric attack mitigation for your OpenClaw server. Check protection options and prices when ordering.
Grow without reinstalling
Add vCPU, memory and disk from the panel and pay only the difference, and OpenClaw stays exactly as it is.
API and MCP for automation
Create, resize and manage servers through the public API — or straight from an AI assistant, over MCP.
Related applications
Open WebUI + Ollama
Open WebUI
A ChatGPT-style AI chat with models that run on the server itself: Open WebUI and Ollama installed on your VPS, one model ready to use.
from R$89.90/moView details →n8n
n8n
Automate leads, support and connections between systems with visual workflows on your own VPS.
Recommendedfrom R$59.90/moView details →Evolution API
Evolution API
WhatsApp API that links numbers to chatbots, n8n and your systems, with the Manager and PostgreSQL, installed on your VPS behind HTTPS.
from R$59.90/moView details →Dify
Dify
Dify installed and configured on your own VPS, ready to use minutes after checkout.
from R$89.90/moView details →
Know what to expect from day one.
Ready infrastructure, with the freedom to configure your application your way.
With your VPS
Your chosen image installed, the plan’s resources and a panel to manage the server. Administrative access is provided after provisioning.
Configure for your business
The app comes up installed and you get the access details when the server is ready. Model providers’ API keys are yours, and usage is billed by them, separately from the VPS.
Expand when you need to
Backups, snapshot capacity, DDoS protection, private networking and other features are available as you need them. Check prices and availability when configuring your server.
You administer the system and application, including updates and data. For help with configuration or management, talk to our team about the scope of support.