The isolation model is different — instead of protecting the developer's machine, we're protecting the enterprise's network from the agent. NetworkPolicies + FQDN egress control per agent namespace.

Question: how do you handle persistent state across sessions? If the agent needs to remember what it learned from a previous run, does the tmpfs model break that?

We ran into the same problem from the infrastructure side. When you're running agent workloads on Kubernetes, the blast radius of a leaked credential scales with whatever the pod's ServiceAccount can reach. We ended up combining Cilium FQDN egress policies (agents can only call approved endpoints) with per-workload tool allowlists enforced at the CRD level. The network-level lockdown means even if the agent is prompt-injected, it physically cannot exfiltrate to an unauthorized domain.

Curious: have you tested AV with agents that make tool calls through MCP servers? The proxy would need to handle the MCP server's outbound requests too, not just the agent's direct calls.