News for hackers. Stuff that matters.
Re:Ask HN: What's your current AI agentic setup? by alentred on Thursday November 05, 2026 @11:04AM (#50380849)
My work is mostly just Claude Code and Codex, but always in a Docker Sandbox. I find it almost the only reasonable way to run the harness safely, never run those on my laptop directly.

I am now working on reproducing a similar setup in a cloud VM + LXC, as opposed to running it on my laptop. The idea is to be able to spawn and provision disposable VMs with some automation and let them work in the background without a need to keep my laptop on `caffein[at]e`.

OpenHands [1] seems like an interesting solution in this setup, too, but I am not yet sold on it.

[1] https://www.openhands.dev/

Re:Ask HN: What's your current AI agentic setup? by 2ero_wf on Monday November 09, 2026 @01:04PM (#50429130)
i just give agent a VM, whether the agent is hermes or claude code. i made sure the VM sleeps when idle, and i made sure i can copy, resize, delete VM when i want to change my setup.

I have 6 VMs hosting claude code coding agent, 2 hermes agent, 1 pi agent when i am out of claude sub, 2 other host some personal-saas softwares. all in VMs.