Sandboxed execution for AI agents

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

Usage

your_agent.py
from cerver import Sandbox
from openai import OpenAI

client = OpenAI()
sandbox = Sandbox()

def handle_message(user_msg):
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": user_msg}],
        tools=[{"type": "function", "function": {
            "name": "run_code",
            "parameters": {"code": {"type": "string"}}
        }}]
    )
    code = response.choices[0].message.tool_calls[0]
    result = sandbox.run(code)
    return result.output
output
User: Analyze the sentiment of our
      latest customer reviews

Agent: I'll analyze that for you.
▸ Running code...

Agent: Found 847 reviews.
       72% positive, 18% neutral, 10% negative.
       Top keywords: "fast", "reliable", "easy"

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

01

Install the SDK

pip install cerver

02

Create a sandbox

One API call spins up an isolated Linux environment.

03

Execute code

Run any code your AI agent generates. Safely.

04

Get results

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

05

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.