News for hackers. Stuff that matters.
Re:Ask HN: What's your current AI agentic setup? by auslegung on Wednesday November 04, 2026 @11:20AM (#50367803)
How about, what sandboxing are you using to prevent the LLM from doing something you don’t want? I’m using nono.sh and have restricted network and file access. I use nono’s proxy so the LLM never gets access to api keys. I create a separate api key for each service specifically for LLM usage, and I restrict those keys as much as possible
Re:Ask HN: What's your current AI agentic setup? by warpspin on Wednesday November 04, 2026 @02:43PM (#50370525)
Tried nono.sh but it seemed cumbersome. I think it lets the whole agent run in the sandbox, so whenever you need to change something, you have to restart the whole thing, if I remember right.

Also tried Docker Sandboxes which worked fine during the try out but my trust in Docker products with regards to security is low in general, so I'd wanted to wait a bit whether problems show up.

Then used Codex for the built-in sandbox but it's buggy like hell, documented features just do not work properly. Nobody there every seemed to actually try using the stuff they are documenting as working.

Ended up with 3code right now, which also has built-in configurable sandboxing.

Re:Ask HN: What's your current AI agentic setup? by sharathr on Wednesday November 04, 2026 @03:27PM (#50371043)
Re:Ask HN: What's your current AI agentic setup? by mickael-kerjean on Wednesday November 04, 2026 @07:16PM (#50373293)
I have been working on a shared folder that sync between agents that connect to whatever storage you already have: S3, SFTP, NFS, SMB, ... The control plane [1] handles the various storages, controls and monitoring and the sync client is at the edge [2] to synchronise everything.

[1] https://github.com/mickael-kerjean/filestash

[2] https://github.com/mickael-kerjean/fdrive

Re:Ask HN: What's your current AI agentic setup? by h45x1 on Thursday November 05, 2026 @01:59AM (#50376030)
I wrote my own bash wrapper around bubblewrap and pasta: https://github.com/andrei-dubovik/jail

The wrapper also keeps history, memory, etc. split by project folder, so agents working in different projects don't know each others' history. If anything, `--resume` is a split second easier.

Re:Ask HN: What's your current AI agentic setup? by salt-licker on Thursday November 05, 2026 @03:53AM (#50376836)
I built something which auto-containerizes the agents for you (with credential isolation and url allowlist), but still allows orchestration between the agents, and a desktop app as well: https://github.com/bsklaroff/yaac