Nomos – an execution firewall for AI agents

(github.com)

2 points | by prudhvinomos 5 hours ago ago

3 comments

  • prudhvinomos 5 hours ago

    Nomos is trying to make that boundary explicit at execution time, but I’m curious how others are handling it today.

    For example: - do you restrict tools at the framework level? - rely on sandboxing? - or allow broad access and rely on monitoring/audit?

  • Lazar71 4 hours ago

    [dead]

  • prudhvinomos 5 hours ago

    [dead]