Give your AI agents a permanent cloud computer.

Choose a developer pod if you work in a terminal and want a computer that stays on and that you run yourself: the agents you already use come installed, and you sign in to each with your own plan or API key. Choose a managed pod if you want a personal AI agent you message from the apps you already use, with nothing technical to do: we set up OpenClaw, secure it, keep it up to date and run it for you, with model usage included.

A real computer in the cloud, and your agent’s alone. It’s the Mac Mini people buy to give their agent somewhere to live, without the Mac Mini: it has its own files and its own browser, it installs the tools it needs, and it keeps all of that through every restart. Nothing on it is shared with other customers, and it stays on around the clock.

Not for OpenClaw. There’s nothing to install and nothing to code: you name your agent and pay, and we build the computer, install your agent and secure it. From there you talk to it in plain language. A developer pod is for developers: you are its administrator, and you work on it from a terminal.

With OpenClaw, yes: your plan covers your agent’s model usage up to a monthly limit. When it runs out, your agent’s thinking on the plan’s usage pauses until your plan renews. Nothing is lost, and we email you when it’s running low. To keep going right away, move to a bigger plan from your pod’s page (Pod Plus at $59 a month with $40 of usage included, Pod Pro at $99 with $80), or add your own model key, and we add nothing on top. With your own key the price stays the same, since it pays for the pod itself, and your included usage stays there for you to switch back to. On a developer pod, no: you sign in to each agent with your own subscription or API key, and your sign-ins never pass through us.

An email address and a way to pay: a credit or debit card, Apple Pay or Google Pay. Prices are in US dollars, and the checkout shows your total in your own currency where supported, with tax added where it applies. A developer pod also needs a Tailscale account, which is Tailscale’s own and separate from Everpod.

Every agent here comes one of two ways: set up and run for you, or installed on a developer pod, which you run yourself. OpenClaw comes both ways; Hermes, Claude Code, Codex, OpenCode and Pi can come installed on a developer pod, ticked when you start it. Any other agent, or an open model’s tools, installs and runs there as on a laptop. Want another agent set up and run for you? Tell us at support@everpod.ai.

Yes. It can start a pod of either kind for you through the Everpod API, and you pay for it yourself. On a developer pod, 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.

Every pod has at least 2 vCPUs, 4 GB of RAM and 40 GB of storage. A developer pod comes in 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. Pods are hosted in Europe.

What’s on your pod lives on your pod, not in our systems: we don’t collect it, read it, or train anything on it. We open what’s on an OpenClaw pod only with your permission during support, or where security, an abuse investigation or the law requires it. Once you have connected a developer pod, Everpod has no login on it and no key. The full picture, in plain words: Privacy policy.

You can leave anytime, and your pod runs to the end of the time you’ve paid for. 7 days after that, we delete it permanently: the machine, everything on it, and the backups all go with it. The short grace window is there in case you cancel by accident; past it, we don’t hold on to your data.