SmolVM

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

CUA provides open-source infrastructure for Computer-Use Agents, including sandboxes, SDKs, and benchmarks to train and evaluate AI agents that control full desktops (macOS, Linux, Windows).

A local execution sandbox for AI agents that uses Docker to isolate filesystem, network, and processes, enabling safe execution of model-generated code, commands, and tool calls.

Python and JS/TS SDK for running AI-generated code in secure cloud sandboxes with Jupyter-style code interpretation