11–19 of 19 posts
Kinda surprising that this doesn't support Linux. Podman can transparently start microVMs instead of local containers via libkrun as well, which does support Linux: https://josecastillolema.github.io/podman-wasm-libkrun/
I work on Docker Sandboxes. We do support Linux with the newer standalone version (sbx), see here: https://docs.docker.com/ai/sandboxes/
This article is from February - we have since shipped the microvm sandbox engine as a seperate binary: sbx - no docker desktop required, small 50mb binary. https://docs.docker.com/ai/sandboxes/ Not sure how well their work maps to sbx, but there has been multiple releases with features and improvements since then
I usually run OrbStack instead of Docker Desktop on my Mac (Docker Desktop is installed on my system, just not running) and when I tried running sbx, it ignored my OrbStack setup and auto-launched Docker Desktop's daemon instead.
If it's possible to bypass that and tell sbx to use OrbStack instead, I'd love to know how.
Is a container breach really the relevant problem to solve for agents? VMs provide better isolation, that's true. But does it matter? Even sandboxed agents usually have a lot of capabilities. Adding backdoors to code by installing breached packages, abusing some access tokens to cause harm, and much more.
> Adding backdoors to code by installing breached packages, abusing some access tokens to cause harm, and much more.
But it doesn’t mean stricter isolation (ie separate kernel space) is a bad thing. One less attack surface in other words. It’s 100% relevant and matters.
I'm most excited about Microsandbox[0]. They're working on an SDK-first experience so you can build whatever applications you want on top, agents just being just one possibility.
This article is from February - we have since shipped the microvm sandbox engine as a seperate binary: sbx - no docker desktop required, small 50mb binary. https://docs.docker.com/ai/sandboxes/ Not sure how well their work maps to sbx, but there has been multiple releases with features and improvements since then
Is a container breach really the relevant problem to solve for agents? VMs provide better isolation, that's true. But does it matter? Even sandboxed agents usually have a lot of capabilities. Adding backdoors to code by installing breached packages, abusing some access tokens to cause harm, and much more.
This article is from February - we have since shipped the microvm sandbox engine as a seperate binary: sbx - no docker desktop required, small 50mb binary. https://docs.docker.com/ai/sandboxes/ Not sure how well their work maps to sbx, but there has been multiple releases with features and improvements since then