Running background agents in production: lessons from Open-Inspect Register

Secure execution environments for coding agents

Spin up 50,000+ simultaneous code execution sandboxes for production use cases

"Modal was the only infrastructure provider that enabled us to reliably run tens of thousands of app creation sessions in an instant. We’re excited to build with them for the long term."

Anton Osika, CEO & Founder

"Modal lets us deploy new ML models in hours rather than weeks. We use it across spam detection, recommendations, audio transcription, and video pipelines, and it’s helped us move faster with far less complexity."

Mike Cohen, Head of AI & ML Engineering

"Everyone here loves Modal because it helps us move so much faster. We rely on it to handle massive spikes in volume for evals, RL environments, and MCP servers. Whenever a team asks about compute, we tell them to use Modal."

Aakash Sabharwal, VP of Engineering

Let agents run wild, safely

Run code written by coding agents in a secure environment.

Waiting for a command...

Agent's Sandbox

Give agent a task

Spin up secure sandboxes in less than a second

Create Sandboxes with one line of code. Modal’s container runtime can spin up Sandboxes with custom images in seconds.

Scale to 50,000+ concurrent sandboxes

Stay one step ahead of customer demand. Modal’s global capacity pool supports massive scale with minimal ops.

Build any coding agent workflow

AI app generator

Build and iterate on end-to-end applications.

Background coding agent

Clone development environments and modify & run code.

RL evals

Massively parallelize the evaluation of generated code samples.

LLM code interpreter

Execute code that is generated as part of the response to a prompt.

Advanced primitives to create powerful agents

Tunnels

Enable encrypted communication between Sandboxes and end user sessions.

Memory and filesystem snapshots

Allow your agent to quickly resume code execution from a saved state.

Granular outbound networking control

Prevent LLM-generated code from communicating with outside systems.

Filesystem APIs

Efficiently sync over AI-generated code and other files that are needed for execution.

Built for production scale

Secure gVisor runtime

gVisor provides stronger security and isolation guarantees than common alternatives.

Granular observability

Easily drill in to dashboards, metrics, and logs, down to the individual Sandbox.

SOC2 and HIPAA compliance

Built with Modal

All examples

Deploy vibe coding at scale

Build an AI coding platform for thousands of users

Sandbox a LangGraph agent's code

Run an LLM coding agent that runs its own language models

Build a stateful, sandboxed code interpreter

Execute untrusted Python code in a sandboxed environment

Safely run untrusted Node.js, Ruby, PHP, and more

Execute arbitrary code in your language of choice inside a Sandbox

Spawn RL environments for a coding model

Use GRPO with TRL to spawn reinforcement learning environments for training coding agents

Ship your first app in minutes.

Get Started

$30 / month free compute