Agent 37 Cloudthe persistent-agent API

Grok hosting that remembers where it left off

Run xAI's Grok coding agent on a persistent, always-on Agent 37 Cloud instance from $1.99/mo. Provision it with one API call, hand it long jobs, and come back to a machine that still has the repo, the caches, and the context.

New workspaces get a $1 starter credit: first instance free, no card required.
[01] Persistent

A coding agent on a disposable sandbox starts over every day

Ephemeral sandboxes are built for one-shot tasks: spin up, run, evaporate. Agentic coding work is not one-shot. It spans sessions, accumulates a working tree, installs toolchains, and picks up threads from yesterday. Hosting Grok on a persistent instance means the environment is part of the work, not a cost you pay again every morning.

The working tree survives: no re-cloning, no reinstalling toolchains every session
Long-running jobs finish: migrations and full test suites are not fighting a sandbox lifetime
Scheduled runs execute on a machine that is already up, with warm caches
Whatever Grok wrote yesterday is exactly where it left it

The usual objection to persistence is price, because the box never turns off. Here that objection is $1.99 a month, metered per minute from a prepaid balance, on the same fleet that runs roughly 1,000 live instances today.

[02] How it works

A persistent computer behind one API

Agent 37 Cloud provisions isolated, always-on instances from Docker images. Grok runs from the one-click agent37-grok template, and the API treats it like any other workload.

One-click template

The agent37-grok template is how Grok runs today: one POST and the instance comes up with xAI's Grok CLI preinstalled. Custom images remain for advanced setups.

One POST to provision

POST /v1/instances provisions a persistent computer running your image on always-on compute. Each instance is an isolated machine with its own disk.

A URL per instance

Every instance is reachable at https://{id}.agent37.app, with any port routable. No reverse proxy, no DNS, no certificates.

Streaming built in

POST /v1/responses on the instance URL runs a turn and streams text, reasoning, and tool activity over Server-Sent Events.

State that stays

Files, memory, and sessions persist until you delete the instance. Checkouts, dependencies, and half-finished branches are waiting next session.

Kernel-level isolation

Every instance runs under the gVisor runtime with a hard per-instance disk quota. Delete the instance anytime and billing stops.

[03] Pricing

What always-on actually costs

Estimated monthly cost of keeping a roughly 4 GB box on 24/7. Sandbox platforms are great at what they are for; a machine that never turns off is not what they are for.

Agent 37 Cloud$1.99/moAlways-on, 2 vCPU / 4 GB, metered per minute
AWS / GCP~$30/moEstimated always-on 4 GB box, before you build the routing and isolation yourself
E2B / Daytona~$121/moEstimated at always-on sandbox rates; these products are priced for ephemeral use

The 2 vCPU / 4 GB shape is $4.94/mo, and disk expands at $0.09 per GB per month. Everything is metered per minute from a prepaid balance: no seats, no minimums, and billing stops the moment you delete an instance.

[04] What you need

Three things, and one of them is free

Grok is a third-party tool: xAI builds it, you license it from them, and this page never pretends otherwise. Here is the full list.

1

Your xAI API key

Grok is xAI's coding agent, not ours. You bring your own xAI API key, and xAI bills you for model usage directly. We host the computer it runs on.

2

The agent37-grok template

Nothing to package: create the instance with the agent37-grok template and it comes up with Grok preinstalled. Set XAI_API_KEY when you create the instance and the first turn just works; the CLI reads the key straight from the environment.

3

An Agent 37 Cloud workspace

Sign in, mint an API key, and provision. New workspaces get a $1 starter credit, roughly a week of the cheapest instance, so the first instance is free and needs no card.

[05] Unattended

Schedule it. Ship it under your own brand.

Scheduled and cron runs

Give an instance a cron schedule and it runs unattended: overnight batch fixes, dependency updates on a timer, a code-health report before standup. A persistent machine means every scheduled run starts warm.

White-label by default

Reselling a coding-agent service? You hold the API key, provision one instance per customer, and cap per-instance spend. Your customers see your brand, never Agent 37.

[06] FAQ

Grok hosting questions, answered

Is there a one-click Grok template?

Yes, available now: the template is named agent37-grok. POST /v1/instances with that template and the instance comes up with xAI's Grok CLI preinstalled. Set XAI_API_KEY in the instance env at create time and chat through the API immediately. The persistence, streaming, scheduling, and isolation described on this page all apply.

What does Grok hosting cost?

From $1.99/mo on a shared instance, or $4.94/mo for a dedicated always-on 2 vCPU / 4 GB instance. Extra disk is $0.09 per GB per month. Everything is metered per minute from a prepaid balance with no seats, and billing stops the moment you delete an instance. New workspaces get a $1 starter credit, so the first instance is free to try, no card required. Model usage is separate: you pay xAI directly through your own API key.

Can Grok run 24/7 here?

Yes. Instances are persistent and always-on by design. A refactor that takes all night keeps running after you close your laptop, and cron-style scheduled runs execute unattended so the results are waiting in the morning.

Where does my code and data live?

On your instance's persistent disk, inside an isolated container running under the gVisor runtime with a hard per-instance disk quota. Files stay on the instance until you delete it, and you can delete anytime. Your xAI key lives on your instance and goes from there to xAI; we never need it.

Is Grok an Agent 37 product?

No. Grok is xAI's coding agent, and it needs your xAI API key to run. Agent 37 Cloud is the infrastructure layer: a persistent, isolated, always-on computer with an API for provisioning, streaming, files, and schedules. The same platform also hosts the open-source Hermes agent and OpenClaw, and any public Docker image.

Can I host Claude Code or Codex the same way?

Yes: Anthropic's Claude Code and OpenAI's Codex each have their own one-click template, agent37-claude-code and agent37-codex, on the same API and pricing. See their hosting pages for the details.

Also hosting a different coding agent? The same API runs Anthropic's Claude Code, OpenAI's Codex, OpenCode, and any public Docker image. Full API details live on the Cloud page.

Start on Agent 37 Cloud$1 starter credit for new workspaces. Delete anytime.