Agent Safehouse – macOS-native sandboxing for local agents

Re:Agent Safehouse – macOS-native sandboxing for local agents by matifali on Sunday March 08, 2026 @08:48PM (#47303435)

I wonder why you believe that running agents locally is the best approach. For most people, having agents operate remotely is more effective because the agent can stay active without your local machine needing to remain powered on and connected to the internet 24/7.

[ Parent | on HN ]

Re:Agent Safehouse – macOS-native sandboxing for local agents by NegativeLatency on Sunday March 08, 2026 @08:51PM (#47303453)

It’s nice having control and ownership of your software.

I’m assuming it’s similar to why people run plex, web servers, file sharing, etc

Also personally I’d rather not pay monthly fees for stuff if it can be avoided.

[ Parent | on HN ]

Re:Agent Safehouse – macOS-native sandboxing for local agents by paxys on Monday March 09, 2026 @12:03AM (#47304770)

These agents are all calling APIs that are well beyond your control. How does it matter whether a thin CLI wrapper is running on your computer or not?

[ Parent | on HN ]

Re:Agent Safehouse – macOS-native sandboxing for local agents by mikodin on Sunday March 08, 2026 @09:14PM (#47303646)

Piggybacking on this - I think it well equips us for a future when local models are stronger. I for one am grateful for efforts like these

[ Parent | on HN ]

Re:Agent Safehouse – macOS-native sandboxing for local agents by deevus on Sunday March 08, 2026 @09:10PM (#47303609)

For this specific problem I built pixels: https://github.com/deevus/pixels

It supports running on a TrueNAS SCALE server, or via Incus (local or remote). I'm still working on tightening the security posture, but for many types of AI workflows it will be more than sufficient.

[ Parent | on HN ]

Re:Agent Safehouse – macOS-native sandboxing for local agents by sunnybeetroot on Monday March 09, 2026 @01:44AM (#47305257)

It’s nice to debug Apple platform projects immediately

[ Parent | on HN ]