Skip to main content

Runloop Platform Features

The Runloop Platform provides many features to simplify and automate your AI coding and agent-based workflows.

Devbox

This is the Runloop sandbox environment where you can run agents and safely test agent-generated code.

Blueprints

A set of instructions for setting up a Devbox with the environment you need.

Blueprint Images

Pre-built disk images with the environment specified by a Blueprint. This allows lightning-fast startup for your Devbox since library installation and other setup tasks are already done.

Snapshots

These are saved copies of the disk state from a running Devbox. Snapshots allow you to suspend your work and pick up where you left off, or fork multiple new Devboxes from a known starting point.

Suspend/Resume

Devboxes can be suspended at any time, and resumed when needed later on.

Code Mounts

Automatically pull the latest code from a repository or pick from a preferred branch. The repository will be ready for use as soon as the Devbox starts up.

Repo Connect

Runloop’s Repo Connect will automatically analyze your code, discover libraries and build tools, and set up a working Devbox Blueprint for you. Works with a wide variety of build and tool environments.

Benchmarks

Create custom benchmarks or select from state of the art hosted benchmarks to train your agent to improve agent performance, detect regressions or make comparisons.

SDKs

Interact with the Runloop platform via high-level object-oriented SDKs. Currently available for TypeScript and Python.

Platform APIs

Runloop has a comprehensive set of HTTP APIs to allow programmatic access. Our api reference contains examples in many languages.

Storage Objects

Managed data and file storage for Blueprints and Devboxes.

Docker-in-Docker

A Docker-in-Docker environment for running Docker containers within a Devbox.

Browser

A remotely-controllable Playwright browser.

Computer

A remotely-controllable Ubuntu Desktop environment.