Instant deployment • Full root access • Crypto payments

Hermes Agent VPS Hosting

Run Hermes Agent from Nous Research on an always-on VPS: its memory, skills and scheduled tasks keep working while you are away, and you talk to it from Telegram, Discord, Slack or the terminal. Full root access, DDoS protection and instant deployment.

Read the setup guide

Hermes Agent VPS at a glance

Recommended system: Ubuntu 24.04 LTS
Memory: 4 GB RAM recommended; 8 GB with browser tools or Docker
Runtime: Python and Node.js, set up by the installer
Chat apps: Telegram, Discord, Slack, WhatsApp, Signal and the CLI
Licence: Open source (MIT)
Deployment: Ready in minutes, with full root access

Choose your Hermes 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 Hermes Agent VPS

What is Hermes Agent VPS hosting?

Hermes Agent is an open-source AI agent from Nous Research. It keeps a memory across sessions, turns completed work into reusable skills, searches its past conversations and can run tasks on a built-in scheduler. You choose the model provider, such as Nous Portal, OpenRouter or OpenAI.

A Hermes Agent VPS gives it a permanent home: the messaging gateway stays online, scheduled tasks run on time, and its memory and skills build up in one place. We provide the server; you install Hermes and bring your model keys.

Why run Hermes Agent on a VPS

Scheduled tasks run on time

The built-in scheduler needs a machine that is on; a VPS never sleeps.

Memory in one place

Its memory, skills and history stay on one server instead of being spread across devices.

Reach it from anywhere

The messaging gateway keeps Telegram, Discord or Slack connected around the clock.

Separate from your computer

Its terminal tools work on a server that holds only what you put there.

Hermes 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 Hermes Agent VPS

A personal research assistant

Ask it to look things up and remember what you care about.

Daily reports by message

Schedule summaries and send the results to Telegram or Slack.

Server and coding tasks

Let it run commands and scripts in its terminal, locally or in Docker.

Skills that improve over time

Repeated work becomes a reusable skill the agent refines as it uses it.

A team assistant

Run it in a team chat with an allowlist of who may use it.

How much VPS does Hermes Agent need?

What you run	Recommended resources
One personal agent	2 vCPU, 4 GB RAM
Browser tools or Docker terminal	4 vCPU, 8 GB RAM
Several agents or heavy scheduled jobs	8 vCPU, 16 GB RAM

How to set up Hermes 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 Hermes Agent
Install Git and curl, then run the official installer as your agent user. It sets up its own Python and Node.js.
```
sudo apt install -y git curl
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
```
5
Run the setup wizard
Choose your model provider and model, then check the installation.
```
hermes setup
hermes doctor
```
6
Connect a chat app
Add your bot credentials and allow only your own user IDs, for example with TELEGRAM_ALLOWED_USERS. Unknown users are denied by default.
```
hermes gateway setup
```
7
Keep the gateway running
Install the gateway as a systemd user service, enable lingering so it survives logouts and reboots, and follow its logs.
```
hermes gateway install
hermes gateway start
sudo loginctl enable-linger $USER
journalctl --user -u hermes-gateway -f
```

Security basics for Hermes Agent on a VPS

Use allowlists or DM pairing, and never allow all users on a bot that has terminal access.
Keep command approval on, and consider the Docker terminal backend to isolate commands from the host.
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.

Troubleshooting

hermes: command not found

Open a new shell so ~/.local/bin is on your PATH.

Something is not working

Run hermes doctor; it diagnoses common problems.

Bot does not answer

Check that your user ID is on the allowlist or approved with hermes pairing approve, and read the gateway log.

Gateway stops after you log out

Enable lingering with sudo loginctl enable-linger $USER.

When you don't need a Hermes Agent VPS

You only chat with it now and then

If you don't need scheduled tasks or a messaging gateway, running Hermes on your own computer is enough.

You want to run large models locally

Hermes works with hosted models on any plan, but local inference of large models needs a GPU server.

Other AI agents you can host

AI agent VPS hostingAlways-on servers for AI agents.

Claude Code VPS guideA remote coding workspace for Anthropic's terminal coding agent.

OpenClaw VPS guideAn always-on personal assistant you reach from WhatsApp, Telegram, Discord and more.

NemoClaw VPS guideNVIDIA's tool for running OpenClaw agents inside a sandbox.

Paperclip VPS guideRun a whole team of AI agents as a company, with goals, budgets and approvals.

PicoClaw VPS guideAn ultra-lightweight assistant written in Go: one small binary, many chat apps.

Official Hermes Agent resources

These links go to the official project sites, in English.

Hermes Agent VPS FAQ

Can I run Hermes Agent on a VPS?

Yes. Hermes supports Linux and is designed to run on inexpensive servers, with its gateway installed as a systemd service.

Do I need a GPU?

No, not with hosted model providers such as Nous Portal, OpenRouter or OpenAI. The VPS runs the agent, not the model.

Which model providers can I use?

Nous Portal, OpenRouter, OpenAI, your own compatible endpoint and others. Switch at any time with hermes model.

Who can talk to my agent?

By default, nobody until you add their user ID to an allowlist or approve a pairing code they receive by direct message.

How do I update Hermes?

Run hermes update. Back up ~/.hermes first, since it holds your configuration, memory and skills.

Which plan should I choose?

4 GB of RAM suits one personal agent. Choose 8 GB if it uses browser tools or a Docker terminal, and 16 GB for several agents.

Does ClientVPS provide API keys or model access?

No. We provide the server. Hermes Agent uses your own account with a provider such as Nous Portal, OpenRouter or OpenAI, or your own compatible endpoint, and you pay the provider directly.

Do you install and run the agent for me?

No. Our VPS plans are self-managed: you install Hermes Agent yourself, run hermes setup and install its gateway as a service. The setup steps above show each command.

How can I pay?

The Hermes 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 Hermes Agent around the clock?

Pick a plan, deploy Ubuntu in minutes and follow the guide above. Pay with crypto or your account balance.

Hermes Agent is an open-source project by Nous Research. ClientVPS is not affiliated with or endorsed by Nous Research.