Compute in a real microVM
Every box is a virtual machine with its own Linux kernel, sized when you create it — up to 4 vCPU and 32 GiB of memory. Hardware isolation, not a shared kernel.
Build and ship with your coding agent. BoxLite runs your app in the cloud and gives you a public URL to share.
what you get
Every box is a virtual machine with its own Linux kernel, sized when you create it — up to 4 vCPU and 32 GiB of memory. Hardware isolation, not a shared kernel.
Publish a box and every service port gets a URL you can open and share. Outbound traffic can be pinned to an allowlist, so the box reaches only what you named.
Around 10 GiB of real disk per box. Packages, files and environment are still there after a stop and a start, so you are not rebuilding the world on every boot.
Mount a managed volume by a name you choose and the data survives the box that wrote it. Volumes are not metered — you pay for the box, not the bytes it keeps.
quickstart
01from boxlite import Boxlite, BoxliteRestOptions02from boxlite import ApiKeyCredential, BoxOptions03import os0405rt = Boxlite.rest(BoxliteRestOptions(06 url=os.environ["BOXLITE_REST_URL"],07 credential=ApiKeyCredential(os.environ["BOXLITE_API_KEY"]),08))0910box = await rt.create(BoxOptions(image="python"))11await box.start()1213result = await box.exec("python", args=["-c", "print(2 + 2)"])14print(result.stdout)/api/boxCreate a microVM./api/box/{id}State, image, network, and whether it is public./api/box/{id}/ports/{port}/preview-urlA public address for a port inside it./api/box/{id}/public/{bool}Publish it, or take it back./api/box/{id}/autostop/{seconds}Idle lifecycle. Zero disables it./api/volumesStorage with a lifetime of its own./api/box/{id}/telemetry/logsWhat the box has been doing.use cases
An autonomous coding agent confined to a microVM.
The agent gets root inside its own kernel and nothing at all outside the box.
A model writes Python; it executes in a disposable microVM.
Generated code never touches your host, and the box is thrown away when it is done.
Tests and an automated review of code you have not read.
Clone the PR into a box, run the suite, then read the diff — with no access to your machine.
CSV in, model-written pandas analysis and a chart out.
The model installs what it needs and writes files; you get the artifact back.
A browser box plus a parsing box, feeding clean data to a model.
Playwright and CDP are ready in the browser box; parsing runs in a separate one.
A live, stateful shell per user, branch, or agent.
State survives stop and restart, so every user or branch keeps its own environment.
local or cloud
| Local | Cloud | |
|---|---|---|
| Where boxes run | Your laptop, your servers, air-gapped | BoxLite's managed fleet |
| How you reach it | In-process library, no account | REST URL + SDK |
| You operate | Hosts, image cache, capacity | Nothing |
| Isolation | Hardware microVM, own kernel | Hardware microVM, own kernel |
| Storage | Your own disk | Managed volumes and cloud disks that outlive the box |
| Box lifecycle | You manage it | Idle-stop and wake-on-access |
| Concurrency | As far as your own hardware goes | Thousands of concurrent boxes |
| Support | Discord and GitHub issues | Dedicated support for Cloud customers |
| Best for | Local dev, embedding in your app, on-prem | Production agents, bursty scale, teams |
pricing
Get an agent into production.
For agents carrying real traffic.
Fleet-scale parallel agents.
Per-box ceilings apply on every plan: 4 vCPU, 32 GiB memory, 120 GiB storage. Included quota covers usage first; a prepaid wallet funds the rest. Full billing docs
faq
Yes. The docs describe Cloud as a hosted agent runtime built on BoxLite — the same SDK and the same core API, reached with a URL and an API key, with managed storage and a managed box lifecycle.