Show HN: Klaus – OpenClaw on a VM, batteries included

Post by docybo » Fri, Mar 13, 2026, 12:10 PM UTC

lombasihir wrote: post #68

docybo wrote: post #62

Feels like most agent security discussions focus on where the agent runs (VMs, sandboxes, etc), but not whether the action itself should execute. Even in a locked-down VM the agent can still send emails, spin up infra, hit APIs, burn tokens. A pattern we've been experimenting with is putting an authorization boundary between the runtime and the tools it calls. The runtime proposes an action, a policy evaluates it, an…

agree, maybe use threadlocker-like mode? confirm any action before it ran, but then it defeat the purpose of autonomous agents.

Post by gbro3n » Sat, Mar 14, 2026, 8:37 AM UTC

hhh wrote: post #86

gbro3n wrote: post #81

Earlier quoted context omitted.

I saw that the Hetzner matrix like has GPU servers < £300 per month (plus set up fee). I haven't tried it but I think if I was getting up to that sort of spend I'd be setting up Ollama on one of those with a larger Qwen3 max model (which I hear is on par with Opus 4.5?? - I haven't been able to try Qwen yet though so that could be b*****ks).

I have tried most of the major open source models now and they all feel okay , but i’d prefer Sonnet or something any day over them. Not even close in capability for general tasks in my experience.