While experimental, we're really excited about this; we've been doing hardware and OS-level virtualization in Docker for a decade, and we are confident this is the right way to isolate coding agents. Besides being more secure than other approaches, this gives you an agent-neutral way to codify your workflow. We've got a lot of features coming behind this initial release that will help your agents cooperate (or compete!).
We just introduced Docker Sandboxes as an early experimental preview. They give coding agents a safe, isolated workspace where they can run code, install packages, and modify files without affecting your host system. This initial version works today with agents like Claude Code and the Gemini CLI, with more agent support on the way. Coming next, we’re aiming for stronger isolation through micro-VMs, granular network controls, better secret handling, and the ability to safely run multiple agents in parallel within their own sandboxes. If you’re experimenting with AI agents, give it a try in Docker Desktop 4.50+. Feedback welcome as we continue to shape this. cc: Eric Jia and Kevin Wittek who're leading this work. https://lnkd.in/g89w_UUH
Nice