Nomos – an execution firewall for AI agents(github.com)2 points·by prudhvinomos·4 mesi fa·2 commentsgithub.comNomos – an execution firewall for AI agentshttps://github.com/safe-agentic-world/nomos5 commentsPost comment[–]prudhvinomos·4 mesi fareplyNomos 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?[+]prudhvinomos·4 mesi fa[+]Lazar71·4 mesi fa[+]shreyssh·3 mesi fa(1)
For example: - do you restrict tools at the framework level? - rely on sandboxing? - or allow broad access and rely on monitoring/audit?