AI Agent VPS Hosting
Self-managed VPS hosting for AI agents such as Claude Code, OpenClaw and Hermes Agent: an always-on Linux server with full root access, NVMe or SSD storage and DDoS protection, ready in minutes. Run your agents around the clock, away from your personal computer.
AI Agent VPS at a glance
- Recommended system
- Ubuntu 24.04 LTS
- Memory
- 4 GB RAM for most agents; 8–16 GB for sandboxes, browsers and teams
- GPU
- Not needed with hosted model providers
- Access
- Full root access over SSH
- Network
- Public IPv4, datacenter bandwidth and DDoS protection
- Deployment
- Ready in minutes in Europe, the US and Asia
Choose your AI Agent VPS plan
Live prices. Ubuntu is selected for you on the next page, where you choose the location and pay with crypto or your balance.
Live plans are loading. You can also choose a plan on the deploy page. Deploy your AI Agent VPS
What is AI Agent VPS hosting?
An AI agent VPS is a virtual server where AI agents run full time. The agent software, its memory, tools and chat connections live on the server, while the language model itself usually runs with a provider such as Anthropic, OpenAI or OpenRouter.
Our plans are self-managed: we provide and protect the server, and you install the agents, add your own model accounts and keys, and decide what the agents are allowed to do. The guides below walk you through each one.
Why run AI Agent on a VPS
Always on
Agents keep working, answering and running scheduled tasks when your computer is off.
Isolated from your personal data
Agents that run commands do it on a separate server, not next to your documents and passwords.
Reachable from anywhere
Connect over SSH or through your chat apps from any device.
Dedicated resources
KVM virtualisation with dedicated vCPU and RAM, and plans from 4 to 16 GB of memory.
AI Agent on a VPS or on your own computer
| What matters | Your own computer | ClientVPS server |
|---|---|---|
| Uptime | Stops when your computer sleeps, restarts or loses its connection. | Runs around the clock in a datacenter. |
| Isolation | The agent can reach your personal files, browser sessions and saved passwords. | A separate machine that holds only what you put on it. |
| Access | Tied to one device. | Reach it over SSH from your laptop, phone or another computer. |
| Network | Home connections are slower and often block incoming connections. | A fast datacenter connection, a public IP address and DDoS protection. |
| Starting over | Undoing an agent's changes to your own computer can be hard. | Reinstall the system from your client area in minutes. |
What you can do with a AI Agent VPS
Coding agents
A remote workspace for Claude Code and similar tools, next to your repositories.
Personal assistants in chat apps
OpenClaw, Hermes Agent or PicoClaw answering on WhatsApp, Telegram or Discord.
Scheduled background work
Reports, monitoring and routine jobs that run on a timer.
Teams of agents
Paperclip coordinating several agents with goals, budgets and approvals.
Sandboxed experiments
NemoClaw or Docker to test agents and guardrails safely.
AI agents you can host
Each guide covers requirements, the right plan size, setup commands from the official docs and security basics.
Plan before you deploy
- Pick the agent and check its memory needs in its guide.
- Decide who owns the server and who may talk to the agent.
- Create separate API keys for the agent, with spending limits.
- Plan where its data lives and how you will back it up.
- Keep dashboards private: SSH tunnel or a private network, not a public port.
- Start with low-risk tasks before giving the agent access to anything important.
How much VPS does AI Agent need?
| What you run | Recommended resources |
|---|---|
| Claude Code, OpenClaw, Hermes Agent or Paperclip | 2 vCPU, 4 GB RAM to start |
| Browser automation, Docker or several agents | 4 vCPU, 8 GB RAM |
| NemoClaw | 4 vCPU, 8 GB RAM minimum; 16 GB recommended |
| PicoClaw | Any plan |
How to set up AI Agent on your VPS
Commands follow the official documentation as of October 2026. Tools like this change quickly, so check the official docs linked below before you run them.
- 1
Deploy a server and connect
Choose a plan with Ubuntu 24.04. When it is ready, connect over SSH with the IP address and password from your client area, and update the system.
ssh root@YOUR_SERVER_IP apt update && apt upgrade -y - 2
Create a user for the agent
Create a normal user with sudo rights, then sign in again over SSH as that user, so the services you install run under it. Add your SSH public key to /home/agent/.ssh/authorized_keys to log in with a key.
adduser agent usermod -aG sudo agent exit ssh agent@YOUR_SERVER_IP - 3
Turn on the firewall
Allow SSH first, then enable the firewall. Dashboards stay on localhost, so no other ports are needed.
sudo ufw allow OpenSSH sudo ufw enable - 4
Install the basics
Git, curl and tmux are used by almost every agent guide.
sudo apt install -y git curl tmux - 5
Follow the guide for your agent
Each guide below has the official install commands, how to keep the agent running and how to reach it safely.
tmux new -s agent
Security basics for AI Agent on a VPS
- Sign in with SSH keys and turn off password logins.
- Run the agent as a normal user, not as root.
- Turn on a firewall and open only the ports you need, usually just SSH.
- Keep dashboards on localhost and reach them through an SSH tunnel instead of opening them to the internet.
- Store API keys in the tool's own config or environment files, never in a Git repository.
- Give the agent its own API keys with spending limits, and rotate them if you suspect a leak.
- Install security updates regularly and reboot after kernel updates.
- Back up the agent's data directory before upgrades and big changes.
When you don't need a AI Agent VPS
You want to run large models yourself
Our VPS plans have no GPU. They suit agents that use hosted model providers, not local inference of large models.
You want someone else to run the agent
These are self-managed servers. You install, update and secure the agent yourself.
AI Agent VPS FAQ
What is AI agent VPS hosting?
A virtual server where you run AI agent software around the clock. You manage the agent; we provide the server, network and protection.
Do I need a GPU for AI agents?
No, not when the agent uses hosted models from providers such as Anthropic, OpenAI or OpenRouter. A GPU is only needed to run large models on the server itself.
Can I run several agents on one VPS?
Yes, if the plan has enough memory. Give each agent its own Linux user, and choose 8 GB or more for several agents.
Which operating system should I use?
Ubuntu 24.04 LTS. It is supported by every agent on this page and is what most of their guides assume.
Can I use Docker, Python, Node.js and Git?
Yes. You have full root access, so you can install any runtime or tool your agents need.
Which plan should I choose?
4 GB of RAM for one agent such as Claude Code, OpenClaw or Hermes Agent. 8 GB for browser automation, Docker or several agents, and 16 GB for NemoClaw.
Does ClientVPS provide API keys or model access?
No. We provide the server. Your agents use your own accounts with model providers such as Anthropic, OpenAI or OpenRouter, and you pay those providers directly.
Do you install and run the agent for me?
No. Our VPS plans are self-managed: you install and run your agents yourself, with full root access. The setup steps above prepare the server: a separate user, the firewall, Git and tmux.
How can I pay?
The AI agent VPS plans on this page start at … a month on yearly billing, which saves 15%, or … a month paid monthly. You pay in cryptocurrency, such as Bitcoin, USDT and Monero, or from your ClientVPS account balance, and you only need an email address to sign up.
Ready to run AI Agent around the clock?
Pick a plan, deploy Ubuntu in minutes and follow the guide above. Pay with crypto or your account balance.
Claude Code, OpenClaw, Hermes Agent, NemoClaw, Paperclip and PicoClaw are products of their respective owners. ClientVPS is an independent hosting provider and is not affiliated with or endorsed by any of them.