Sandboxed execution for AI agents

Managed infrastructure for running untrusted code. You build the product. We handle isolation, scaling, and security.

Request access How it works

Usage

your_agent.py

from cerver import Sandbox

sandbox = Sandbox.create()

result = sandbox.run("""
  import pandas as pd
  df = pd.read_csv('data.csv')
  print(df.head())
""")

print(result.stdout)
                    

output

$ python your_agent.py

✓ sandbox created (141ms)
✓ code executed
✓ sandbox terminated

   col_a  col_b  col_c
0   12.4   0.82   True
1   18.7   0.91   True
2    9.1   0.45  False
                    

Features

Fast cold starts

Sandboxes boot in ~150ms. No waiting. Agents run immediately.

Full isolation

Each sandbox is a separate microVM. Network controls, resource limits, no shared state.

Any runtime

Python, Node, Go, Rust. Full Linux. Install packages, run binaries, access filesystems.

Pay per second

Billed for actual execution time. No idle costs. Scales to zero automatically.

Observability

Logs, stdout/stderr, execution traces. Know what your agents are doing.

Simple API

Python SDK and REST API. Create, execute, terminate. Three methods.

How it works

Install the SDK

pip install cerver

Create a sandbox

One API call spins up an isolated Linux environment.

Execute code

Run any code your AI agent generates. Safely.

Get results

Stdout, stderr, exit codes. Sandbox auto-terminates.

Scale to infinity

Run thousands of sandboxes in parallel. We handle the infra.

Pricing

Starter

Pro

Enterprise

Base fee

$0/mo

$129/mo

Custom

Usage

$0.000031/sec

$0.000025/sec

Volume discounts

Support

Community

Priority

Dedicated

SLA

—

99.9%

Custom

Get early access

We're onboarding teams building AI products.

Thanks! We'll be in touch soon.