Run more agents at once than your laptop can hold

A VPS of your own, set up and secured for you. It’s a permanent cloud computer, so Claude Code, Codex, OpenClaw or any agent you use keeps working 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 and walk me through setting it up, following https://everpod.ai/docs/api#developer-pod

Choose your agents.

Tick the ones you want when you start it. 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.

A developer pod in 40 seconds

A developer pod: your pick of Claude Code, Codex, OpenCode and Pi on an always-on cloud computer of your own, set up, private to you on your Tailscale network and signed in with your own plan, running many sessions at once, still working after your laptop closes, and steered from your phone.

This video was made with Claude Code on a developer pod: it drew the scenes and rendered the video. Rendering is heavy work, the kind a pod does so your laptop doesn’t have to.

Your agents get a computer of their own.

Put recurring work on a schedule, and it gets done without you remembering or leaving a computer on.

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

Ubuntu, with you as its administrator. Docker, git, Node, Python, Chrome, ffmpeg, the PDF tools and tmux are there, and you install anything else as you would on a laptop.

Not only code.

People hand these agents the rest of their work too. Here it runs on a computer that stays on.

Research and writing

  • ✓Reads hundreds of pages and drafts the brief while you sleep
  • ✓Chrome is installed, for pages that need a real browser
Pricing briefreading · 23 of 40

You ask: “Read the 40 competitor sites in sites.txt and write a two-page brief on how each one prices.”

Documents and data

  • ✓PDFs by the thousand: the PDF tools and Python are installed
  • ✓Spreadsheets, exports and databases: read, cleaned and written here
Contracts212 of 1,000 PDFs

You ask: “Go through every PDF here and put each contract's renewal date and notice period in a spreadsheet.”

Video, audio and images

  • ✓ffmpeg is installed: it cuts, converts and encodes
  • ✓A render that takes hours runs here, with your laptop shut
Chaptersrendering · 47%

You ask: “Cut the two-hour recording into one clip per chapter in chapters.txt and export each at 1080p.”

The machine, layer by layer.

Your agentsClaude CodeCodexOpenCodePiand anything you install
Your toolsdockergitnodepythonchrometmux
Ubuntu 24.04You are its administrator, and its security updates install themselves.
The hardwareThree sizes: S with 4 vCPU, 8 GB of memory and 80 GB of fast solid-state disk; M with 8 vCPU, 16 GB of memory and 160 GB of fast solid-state disk; L with 16 vCPU, 32 GB of memory and 320 GB of fast solid-state disk.room for about 8, 16, 32 agents working at once
BackupsThe whole disk is backed up daily, and the backups rotate over roughly 7 days.

Reaching it, made easy.

We set up the connection, and your pod’s page shows each step of joining it to your network.

Set up before your first login

Tailscale, the private network between your own devices, comes installed. One sign-in on the machine’s page joins it to your network, and from then on you log in over SSH with no key to make or manage: Tailscale checks it is you.

On all your devices

With Tailscale on your laptop and your phone too, all three are on one private network. Start agents on it from your laptop, then check on them from your phone with Tailscale’s app and any SSH app, and answer one that has stopped to ask you something. Any other device signed in to the same Tailscale account can reach it too, with nothing to set up on the machine.

Your coding agent works on it for you

The coding agent on your laptop reaches the machine as you do, over SSH with no key to manage: ask it to install, start or check on anything there, and it logs in and does it.

Closed to the open internet

It accepts no incoming connections from the open internet: no open ports and no public SSH. A server your agent starts is reachable from your devices and from nowhere else. By default the machine does not start connections to your other devices.

Only you have a login.

1

Built, with our setup access

We build the machine and install what you chose, then email you.

2

You join it to your network and log in

One Tailscale sign-in on its page joins it to your network. Then you switch off its key expiry in Tailscale’s admin console and log in over SSH.

✓

We remove our access

From then on Everpod has no login on it and no key.

We do not log in to fix or update it: security updates install themselves, and the machine is yours to administer. We host the server it runs on, so we can restart it or restore one of its daily backups when you ask us to.

All you do is name your machine.

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

The quickest way: paste this into the coding agent on your laptop. It starts the machine and walks you through these steps.

Get me an Everpod developer pod and walk me through setting it up, following https://everpod.ai/docs/api#developer-pod
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 your agents with your own subscription or API key.

Setting it up, step by step

The developer pod guide starts at your first login: signing in to your agents and to GitHub, cloning your repositories, starting sessions that keep running with your laptop shut, and checking on them from your phone.

Read the developer pod guide

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 a developer pod a VPS?
Yes. A VPS, a virtual private server, is a computer of your own that you rent in a data center: it stays on, and what you put on it stays there. A developer pod is one that arrives set up and secured, with your agents installed and daily backups running, and from then on you administer it as you would any VPS.
How is it different from Codespaces, Coder, Daytona or Gitpod?
Codespaces, Daytona and Ona (as Gitpod is now called) give you an environment that runs when you need it, charged by the hour or the second, and stop it when it sits idle: by default a codespace stops after 30 minutes of inactivity and has a maximum lifetime of 12 hours, and Daytona’s sandboxes and Ona’s environments stop after 15 and 30 minutes. Coder is software a company runs on its own cloud to give its developers such environments, on the schedule it sets. They suit a team that wants the same environment for everyone, built from a repository, an editor in the browser, many short-lived sandboxes started by a program, or light use that costs little. A developer pod is one machine of your own that stays on, with no idle timer and no time limit, so an agent left working overnight is still working in the morning. Its whole disk is kept and backed up daily, the price is the same every month, and the agents you pick come installed.
What do I need to get started?
An email address and a way to pay. You need a Tailscale account, which is Tailscale’s own and separate from Everpod. The machine joins your network with it, and the laptop or phone you log in from needs Tailscale too, signed in to the same account. If your laptop runs a consumer VPN, it may need to be off or set to let Tailscale through.
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.
Which size do I need?
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.
Can I run Docker and leave servers running?
Yes. Docker is installed, you are the machine’s administrator, and a server your agent starts is reachable from your own devices and from nowhere else. Running processes stop if the machine restarts; what is on its disk stays.
Which agents can I run?
Your pick of Claude Code, Codex, OpenCode, Pi, Hermes and OpenClaw comes installed, ticked when you start it, and you sign in to each with your own plan or key. Hermes and OpenClaw here are yours to run, as on a laptop; OpenClaw set up and run for you is the OpenClaw pod. Any other coding agent, or an open model’s tools, installs and runs beside them as on any Linux computer. Claude Code, Codex, OpenCode, the Pi coding agent and Hermes each have a page on how they run there.
Is it only for coding?
No. Whatever you hand Claude Code, Codex, OpenCode, Pi, Hermes or OpenClaw on a laptop, it does here: research, documents, data, video. Ubuntu, with you as its administrator. Docker, git, Node, Python, Chrome, ffmpeg, the PDF tools and tmux are there, and you install anything else as you would on a laptop. What it asks of you is a terminal: you log in over SSH and run the agent there.
Can an agent I already use get me a pod?
Yes. Paste the line at the top of this page into it, and it starts the machine through the Everpod API and walks you through the rest. You pay for it yourself. The coding agent on your laptop reaches the machine as you do, over SSH with no key to manage: ask it to install, start or check on anything there, and it logs in and does it.
How are backups restored?
The whole disk is backed up daily, and the backups rotate over roughly 7 days. Email support@everpod.ai and we restore the day you choose, or restart the machine.
What if Tailscale stops letting me in?
Your way in is your own Tailscale network, so a rule there that shuts you out is put right in Tailscale’s admin console, with nothing on the machine to change. The one to watch is a tag. A tagged machine is no longer one of your own devices, so Tailscale’s default rule for SSH into your own devices stops covering it, and the console cannot take a machine’s last tag off. Add an SSH rule from your own login to the tag before you tag the machine, or add it afterwards to get back in; our guide to Tailscale SSH for an agent server shows one. If you remove the machine from your network or lose your Tailscale account, we have no login with which to restore your access.
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.

Name your machine. Bring your agents.

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