Run Codex on an always-on developer pod
A VPS of your own, set up and secured for you. It’s a permanent cloud computer, so Codex keeps working when your laptop is closed, and you pick its sessions up from your laptop or your phone.
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 Codex installed, and walk me through setting it up, following https://everpod.ai/docs/api#developer-podReal posts from developers who run their coding agents on a machine that stays on. Their words, their own setups.
@levelsio@levelsio · Jun 28“✨ I think I've been coding almost solely on my VPS with Claude Code for almost a year now
All I can say it's just fantastic:
- no need to keep laptop open ever
- no laptop battery drain
- can switch to phone or any other device you like whenever you want to continue (like when you're outside)
- it just keeps going all night while you sleep (esp with /goal)…”Codex 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, OpenCode, Pi, Hermes or OpenClaw too, and they come installed. 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.
Not only code.
People hand Codex 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
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
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
You ask: “Cut the two-hour recording into one clip per chapter in chapters.txt and export each at 1080p.”
Three ways to keep Codex running.
No laptop left open, no server to secure. Your pod arrives set up, and stays on.
OpenAI’s cloud vs an Everpod developer pod.
OpenAI’s cloud runs a task. A developer pod is a computer.
OpenAI’s hosted tasks
A developer pod
OpenAI’s documentation on remote access advises: “Add an always-on computer or SSH host when you need continuous access or a different environment.” A developer pod is that SSH host, and it never sleeps. The ChatGPT desktop app on a Mac or PC can open projects on it too. What each keeps, side by side: the guide
Codex runs here as it does on your laptop.
Use the plan you already pay for
- ✓Plus, Pro, Business, Enterprise or Edu, or an OpenAI API key billed by use
- ✓Approve the one-time code in any browser, on your laptop or your phone
- ✓It needs one switch on ChatGPT’s side: device code sign-in, under Settings, Security and login, or the workspace permission an admin turns on
Its sandbox works from the first command
- ✓The commands Codex chooses write only to your project’s folder
- ✓On a fresh Ubuntu 24.04 server the sandbox fails until bubblewrap may create user namespaces; a developer pod comes with that set
alex@atlas:~/app$ codex sandbox -c sandbox_mode=workspace-write -- touch notes.txt /etc/hello touch: cannot touch '/etc/hello': Read-only file system
Many sessions at once
- ✓Room for about 8 working at once, on your one plan’s limits
- ✓Tick Claude Code too, and one can review the other’s work
All you do is name your machine.
We build it, install Codex and secure it. About 10 minutes later, you 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 with Codex installed, and walk me through setting it up, following https://everpod.ai/docs/api#developer-podName it and choose your agents
Name the machine, choose your username on it, and tick the agents you want installed.
Confirm your email and pay
From $24 a month, cancel anytime. We start building the moment your payment goes through.
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 Codex 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.
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.
Before you decide.
Is model usage included?
Is it only for coding?
Who else can log in to it?
Can I steer it from the ChatGPT app on my phone?
Does it work with a ChatGPT Business workspace?
Does it work on ChatGPT Free or Go?
Can I run Claude Code on it too?
What are its specs?
What happens if I cancel?
Codex, on a computer that stays on.
from $24/mo, cancel anytime · 4 to 16 vCPU, 8 to 32 GB