Novita Sandbox / Built for AI agents

Give your AI agent a place to act

Run code. Run CI/CD with GitHub Actions

Use browsers. Control desktops.

Give every agent an isolated runtime to turn plans into real-world tasks.

Agent executionWorkflow illustration

Agent task

Analyze a dataset. Build a report.

Novita SandboxIsolated runtime
CodeBrowserFiles

01Load data & install dependencies

02Execute Python analysis

03Save charts & report

↳ Output: report.html

Stateful sessionsSDK / CLI
From agent intent to useful outputCode, files and workflows in one environment.
Average instance startup¹
<200ms
Single-round concurrency²
2,500
Sandbox self-build success rate
99%

¹ Average startup reported by Novita; actual latency varies by workload.

² Your account's concurrent sandbox limit follows its tier quota, shown in the pricing section below.

View pricing

Where your agent gets to work

What will your agent do?

Use Sandbox when your agent needs to execute code, interact with software, or keep state across tasks.

01 / Coding agents

Write. Run. Test. Iterate.

Let coding agents install packages, execute generated code and run tests in their own environment.

Example task

Fix a bug, run the test suite, return the patch.

Explore code execution
02 / CI/CD

Review. Test. Validate.

Run code reviews, automated tests and build validation in isolated sandboxes with GitHub Actions.

Example task

Validate a pull request and return test results.

View GitHub workflows
03 / Browser agents

Navigate the web. Get things done.

Run Browser Use workflows to navigate pages, fill forms and extract structured results inside Sandbox.

Example task

Research product pages and export a comparison.

Explore Browser Use
04

Computer Use

Run GUI workflows in isolated desktops with VNC viewing for monitoring and debugging.

Explore Computer Use
05

Data analysis & reports

Process files, run Python analysis and save charts or reports in an isolated filesystem.

06

Agent evaluations & RL

Reuse prepared environments for repeatable evaluation and reinforcement learning workloads.

07

Long-running agent workflows

Preserve filesystem and memory state with pause and resume across multi-step tasks.

The execution layer for your agent

Your agent brings the plan. Sandbox brings the runtime.

Read the documentation

Isolated execution

Give each task its own runtime and filesystem. Run commands and install the dependencies your agent needs.

State that stays with the task

Pause and resume with filesystem and memory intact. Compute billing stops while paused; storage charges can apply.

Reusable environments

Use templates for consistent starting environments and snapshots to reuse prepared sandbox state.

Connect to the outside world

Access external APIs, work with files and connect browser workflows to your agent’s tools.

Pay for the resources you use

Small tasks. Clear costs.

CPU and memory billed per second. No subscription required.

See full pricing

Start small. Scale when you need to.

Free tier: 5 concurrent sandboxes, up to 1 hour per session.

Paid tier: 100 concurrent sandboxes. Session limits and account eligibility follow your account quotas.

Illustrative compute cost

$0.00345-minute task

1 vCPU + 512 MiB RAM

vCPU
$0.0000098 / vCPU-second
Memory
$0.0000032 / GiB-second
Storage
$0.00009 / GB-hour

Compute estimate rounded from published rates; excludes storage and external services such as model APIs. First 60 GB persistent storage included per account. Storage is measured hourly and charged daily.

Your first agent task starts here

Build your first agent workflow. Start with Sandbox.

Explore isolated runtimes for your AI agent.

Get started
  1. 01

    Create your Novita account

    Sign up as a new customer.

  2. 02

    Configure your first Sandbox

    Choose the resources your agent needs.

  3. 03

    Launch your first Sandbox

    Create an API key and follow the SDK quickstart to run your first task.

    Open the quickstart

Before you build

A few useful answers.

What is an AI agent sandbox?

An isolated execution environment where an agent can run code, use browsers, manage files and maintain state. Novita manages the runtime infrastructure so you can focus on the agent workflow.

Can I pause a task and continue later?

Yes. Pausing preserves filesystem and memory state. Resuming restores the environment; killing a sandbox terminates it and it cannot be resumed. Compute billing stops while paused, while storage charges can apply.

Are model API costs included in Sandbox pricing?

Sandbox prices cover the allocated runtime resources. Model API calls and other external services have their own pricing. Review the relevant service prices when estimating a complete agent workflow.

What if I need higher concurrency or custom resources?

The standard paid tier supports 100 concurrent sandboxes. Enterprise options offer custom resource limits and deployment regions.

Contact Novita sales

Build agents that do more

Your agent. Ready for action.

Create an isolated runtime for your next agent task.

Get started