Reference testbed for runtime governance of LLM coding agents — per-agent sandboxing (bwrap + Landlock + cgroups + netns), event-sourced audit trails, three control planes, 9/9-passing breakout tests.
go rust sandbox event-sourcing ecs ebpf agents governance bwrap landlock llm anthropic agent-runtime runtime-governance sandbox-isolation
-
Updated
Jul 15, 2026 - Rust