Like Docker Sandbox this meets what I think should be our standards in the AI age: kernel isolation and secret shielding in addition to network and disk isolation.
I have been working on a similar project because I haven't seen one before that to me didn't have security design deficiencies. This project looks to have made good design decisions around security.
The things that are design choices for these tools are
* agent integration
* docker image composition
* are vms more persistent or throw away
* managing configuration
It does look like it has some design decisions that are optimal for convenience but might lead to inflexibility. It assumes 1 VM per directory. It is trying to auto-detect what someone needs in an image and provide well integrated images and tools out of the box but I don't see how to just provide my own image.