Run Hermes Agent on an always-on developer pod

A VPS of your own, set up and secured, with Hermes installed for you to run yourself. It’s a permanent cloud computer, so it keeps answering your messages and running its schedules when your laptop is closed.

Get your developer podfrom $24/mo, cancel anytime · 4 to 16 vCPU, 8 to 32 GB

Already use a coding agent on your laptop? Paste this into it, and it sets your pod up with you.

Get me an Everpod developer pod with Hermes installed, and walk me through setting it up, following https://everpod.ai/docs/api#developer-pod

Hermes gets a computer of its own.

Not a laptop you have to leave open: a whole Ubuntu machine you administer, always on, set up and secured before you log in.

It’s a real computer, just like your own, so your files, repos, tools and logins persist.

Tick Claude Code, Codex or OpenCode too, and Hermes can delegate coding to them. You are choosing only what comes installed: the computer is yours to administer, and any agent installs or comes off later, as on a laptop. Docker, git, Node, Python, Chrome, ffmpeg, the PDF tools and tmux are there.

Hermes runs here as it does on your laptop, and keeps running.

Use the plan or key you already have

  • ✓A Nous Portal subscription, a ChatGPT sign-in, GitHub Copilot, OpenRouter, or a key for the provider you choose
  • ✓Nous Portal and ChatGPT sign in with a code you enter in a browser on your laptop or phone
Hermes wants to use your Nous accountAAlexNous PortalApprove

Talk to it from Telegram

  • ✓Its gateway stays up after you log out, so Hermes answers with your laptop shut
  • ✓It fetches your Telegram messages itself, so nothing has to open to the internet
ChatsHermesbotHTotal last month’s invoices by client.On it: 18 of 42 read.Skip the refunds.Done.totals.csv2 KB

Schedules that run while you sleep

  • ✓Ask for one in plain words in Telegram, and its results arrive there
  • ✓Its scheduler runs inside the gateway, so a job runs whether or not your laptop is open
Tuesday 13 October7:02HHermes07:00Morning summary: 4 new AI stories on Hacker News.HHermes06:00Server check: all three sites are up.

Hermes’s own docs on what it is: “It’s not a coding copilot tethered to an IDE or a chatbot wrapper around a single API.” And on where it lives: “It’s not tied to your laptop.”

Three ways to keep Hermes running.

No laptop left open, no server to secure. Your pod arrives set up, and stays on.

Where to run Hermes, compared: the guide

All you do is name your machine.

We build it, install Hermes and secure it. About 10 minutes later it’s ready to use: you join it to your network and log in.

1

Set it up and choose your agents

Confirm your email, then name the machine, choose your username on it, and tick the agents you want installed.

2

Choose its size and pay

From $24 a month, cancel anytime. We start building the moment your payment goes through.

3

Join your network and log in

About 10 minutes later it is built, and we email you. Its page lists three steps and ticks each one as you complete it: one sign-in joins it to your Tailscale network, a button opens Tailscale’s page for switching off its key expiry, and the command to log in over SSH is ready to copy. Then sign in to Hermes with your own subscription or API key.

Private by default

Your pod arrives on your own private network, closed to the internet, and yours alone.

On your private network only

Reached only from your own devices, over Tailscale. No open ports and no public SSH: a server your agent starts is reachable from your devices and from nowhere else.

Yours alone

A whole private computer, one customer per machine. Nothing on it is shared with other customers.

Only you have a login

Once you have joined the machine to your Tailscale network, switched off its key expiry and logged in, we remove the access we used to set it up. From then on Everpod has no login on it and no key.

Backed up every day

The whole disk is backed up daily, and the backups rotate over roughly 7 days. We restore one when you ask.

Security updates install themselves

The machine is yours to administer, and its security updates install on their own.

Deletion is permanent

When you cancel, the machine runs to the end of the paid month, is switched off, and is permanently deleted 7 days later, backups included.

You don’t do any of this. Your pod arrives on your private network, closed to the internet.

What your developer pod costs.

Three sizes. The figure is about how many coding agents each has room for at once.

Every size
✓an always-on cloud computer of your own, with admin rights
✓your pick of Claude Code, Codex, OpenCode, Pi, Hermes and OpenClaw installed, with Docker, git, Node, Python and Chrome
✓reached over your own Tailscale network, with nothing open to the internet
✓hosted in Europe
✓no Everpod login on it once you have connected it
✓daily automatic backups
✓cancel anytime
You sign in to each agent with your own subscription or API key. No model usage is included, and your sign-ins never pass through us.

Before you decide.

Is model usage included?
No. Hermes runs on your own plan or API key, billed by whoever provides the model, and the price is for the machine.
Is Hermes set up and run for me?
No. Hermes here is installed for you to run yourself: its setup and updates are yours. What it asks of you is a terminal: you log in over SSH and run the agent there.
Can I use my Claude plan with it?
Hermes can sign in with a Claude account, and its docs say that path “only works on a Claude Max plan with purchased extra usage credits”. Claude Code, which you can tick beside it, signs in with your Claude plan. Claude Code on a developer pod says how it runs there.
Can I run Claude Code, Codex, OpenCode or Pi on it too?
Yes. Tick them too when you start it, with OpenClaw if you want it, or install any of them later as on any computer. Hermes ships with skills that delegate coding to Claude Code, Codex and OpenCode. By default Hermes borrows Claude Code’s and Codex’s sign-ins when it has none of its own; here it arrives with that switched off, which is what its docs advise when they share a machine, and the setting is yours to change. Claude Code, Codex, OpenCode and the Pi coding agent each have a page on how they run there.
Who else can log in to it?
Only you. Once you have joined the machine to your Tailscale network, switched off its key expiry and logged in, we remove the access we used to set it up. From then on Everpod has no login on it and no key.
Can I reach it from my phone?
Yes, two ways. Once its gateway is set up, you message Hermes from Telegram. And with Tailscale’s app and any SSH app on your phone, you log in to the machine as you do from your laptop.
Can I open Hermes’s dashboard from another device?
Yes, the way its docs give for a machine on Tailscale. By default the dashboard is “only accessible from your local machine, with no login required”. Give it a sign-in and bind it to the machine’s Tailscale address, and in the docs’ words, “Only devices on your tailnet can reach it.”
What are its specs?
Three sizes: S with 4 vCPU, 8 GB of memory and 80 GB of disk, room for about 8 coding agents working at once; M with 8 vCPU, 16 GB of memory and 160 GB of disk, about 16; L with 16 vCPU, 32 GB of memory and 320 GB of disk, about 32. You choose the size when you start it. Later you can move it to a bigger size from its settings, keeping the disk it started with, and back down again, never below the size you started with. Each size’s price is on the developer pod’s page.
Can I buy one from my country?
A developer pod can be bought from most countries, outside the US and Europe included. If it cannot be bought from your country, the checkout stops before anything is charged.
What happens if I cancel?
Cancel anytime from your account. The machine runs to the end of the paid month, is switched off, and is permanently deleted 7 days later, backups included.

Hermes, on a computer that stays on.

from $24/mo, cancel anytime · 4 to 16 vCPU, 8 to 32 GB