Guides
How to give AI agents a computer without giving them yours: isolation levels, the policy around a sandbox, and working code for code interpreters and browser agents.
Getting started
Security
Tutorials
- Build a code interpreter with open modelsBuild a ChatGPT-style code interpreter with an open model on gpuOS and a cpuos sandbox: tool schema, agent loop, files, charts and limits, in Python.4 min read
- A browser automation sandbox for AI agentsWhy browser agents need isolation, and how to run headless Chromium and Playwright for an AI agent inside a disposable microVM sandbox.3 min read
Comparisons
- Firecracker vs Docker for AI agentsFirecracker microVMs vs Docker containers for running AI agent code: kernel isolation, startup time, snapshots, density, operations and when each makes sense.4 min read
- An EU-hosted E2B alternative for agent sandboxesLooking for an E2B alternative hosted in the EU? How to compare agent sandbox providers on GDPR, data residency, isolation, pricing and self-hosting.4 min read
Give your agents a computer
cpuos is in early access. Join the waitlist for Firecracker sandboxes hosted in the EU, billed per second and free while paused.
gpuOS · where models think
Need the model too? Run it on gpuOS
gpuOS serves open models on your own GPUs behind one OpenAI-compatible API. The model reasons on gpuOS, the agent acts in a cpuOS sandbox.