This sort of works.

The problem is that you'll end up wanting to run 2 or 3 (or 20, 100, 10,000) agents at once and that gets very hard with a single VM.

There's also an argument that you should be using a separate sandbox for each code operation a LLM performs (or at least each set of related operations). That's even harder to do with conventional VMs.

▲

christophilus 6 hours ago | parent [-]

I just use git worktrees in a single container. Albeit I don’t have more than 3 agents going at a time generally due to my own context switching limitations.

	▲	binsquare 6 hours ago \| parent [-]
		It's a different level of isolation, worktrees help agent work on different code repository in parallel but things get wonky once you consider processes and environments variables