AI that does the work. The cloud it runs on.

Clusterbase makes Cluster — the AI app that answers with sources, sends bots to do the task, and builds apps from a description — and the cloud platform underneath it, open to every developer.

Products

For business

Give every team a few more hands.

Answers with sources, bots that do the task on their own computer, and apps built from a description. One place for the whole company, with the API underneath when you want to build on it.

Answers you can check

Ask searches the live web and answers with citations, so a claim in a deck or a memo traces back to its source.

Bots that finish the task

A Cluster Bot opens a real browser on its own cloud computer, works through the sites your team uses, and reports back.

Internal tools from a sentence

Build turns a description into a running app with a shareable link, and the Build CLI picks the same session up in the terminal.

Solutions

Set up for the work your team already does.

Explore all use cases

For developers

Write a function.
Get a URL.

The platform our own products run on is open to you. Start with a few lines of TypeScript and one command; add a database, a container, or an agent when you need one.

https://my-app.clusterbase.dev

Hello from Clusterbase!

index.ts
export function handler(request: Request): Response {
  return new Response("Hello from Clusterbase!");
}

Sandboxes

Computers for AI. One for every agent.

An agent that can only talk is a chatbot. Give it a computer and it can write the code, run it, open the browser, and check its own work. A Sandbox is that computer: a full Linux machine that starts for the job and is gone when the job is.

One agent, one machine

Run one or run a thousand. Every agent works on its own computer, so a long job, a crash, or a bad idea stays on the machine it happened on.

Testing the checkout flow

Refactoring billing

Reconciling q3.xlsx

Running a backtest

Isolated from everything else

Each Sandbox is its own microVM with its own kernel. Untrusted code runs inside it and stays inside it. The ports you declare stay private, reachable only with a scoped token that expires.

Access to cdpExpires in 5 min

A private address, a scoped token, one declared service. The machine’s own address is never published.

ccp sandbox connect sbx_… cdp --ttl 5m

Built from a recipe

Describe the machine in a YAML file: a base, packages, a setup step. ccp apply turns it into an immutable build, and every launch starts from exactly that.

sandbox.yaml
apiVersion: sandboxes.clusterbase.ai/v1
kind: SandboxTemplate
metadata:
  name: python-tools
spec:
  base: debian
  resources:
    vcpu: 2
    memory_mb: 1024
  packages:
    apt: [jq, python3, python3-venv]

Around as long as the work

Give a Sandbox a lifetime from a minute to a day, or keep it. An idle desktop pauses to free its memory and picks up exactly where it stopped.

  • python-toolsRunning · 11 minutes left
  • desktopPaused while idle · resumes on connect
  • headless-chromeRunning · kept, no expiry

Priced for running a lot of them

One flat hourly price per machine size, billed by the second after a 30-minute minimum, and only while the Sandbox is running. Paused machines cost nothing.

$0.060/ hour

  • Cluster$0.060
  • E2B$0.1171.9x the Cluster price
  • Daytona$0.1171.9x the Cluster price
  • Cloudflare$0.1532.6x the Cluster price
  • Modal$0.1662.8x the Cluster price
  • Vercel Sandboxwith 4 GB$0.3415.7x the Cluster price

Other prices are each vendor’s published per-vCPU and per-GB rates applied to the same machine size, September 2026, for sessions of 30 minutes or more; the others bill shorter runs by the second. Vercel only sells 2 GB per vCPU and bills active CPU, shown here at full use.

Choose how to get started

Use Cluster

Sign up and ask your first question. Free to start.

  • Answers with sources you can check
  • Bots that do the task and report back
  • On web, iOS, and Android
Try Cluster

Bring it to your team

Tell us what your team does all day and we will show you where Cluster fits.

  • Shared workspace for the whole company
  • Works with the tools you already use
  • Dedicated and air-gapped deployments
Talk to Sales

Build on the platform

Install the CLI and deploy your first application in about 60 seconds.

  • Scaffold a project with ccp init
  • Ship with ccp deploy --prod
  • A preview URL for every deployment
Read the Quickstart