Show HN: Nucleus – enforced permission envelopes for AI agents (Firecracker)

Re:Show HN: Nucleus – enforced permission envelopes for AI a... by mcnamtm1 on Monday February 02, 2026 @05:27PM (#46862791)

Very interesting use of Firecracker for agent isolation.

How do you handle network identity for the agents themselves? Are you using something like mTLS/SPIFFE to identify the workload inside the VM, or is it purely network-policy based at the host level? Can you explain the "runtime enforcement" and the "enforcing tool proxy?

[ Parent | on HN ]

Re:Show HN: Nucleus – enforced permission envelopes for AI a... by difc on Monday February 02, 2026 @10:32PM (#46866118)

Thanks! Currently network identity is host-based, but in the middle of introducing SPIFFE based on ZTunnel. Should be done in the next couple of days.

Runtime enforcement means that any side effects are routed through a proxy (nucleus-tool-proxy) that does realtime checks on permissions and gates the behavior.

SPIFFE for MicroVM agents is a compelling idea and I'll update when this is ready.

[ Parent | on HN ]