NVIDIA open-sources Agent Safety Platform with in-silicon monitoring and DPU-level enforcement

NVIDIA 发布开源智能体安全平台，提供芯片级持续监控与隔离

NVIDIA released an open-source agent safety platform that bakes monitoring and enforcement into Vera CPUs and BlueField-4 DPUs. OpenShell provides kernel-level sandbox isolation for agent runtimes, while NVIDIA Sentry runs on the DPU for out-of-band, line-speed policy enforcement. The design follows five principles: verifiable policy, out-of-band enforcement, controlling the path to the model, scaling authority with reasoning visibility, and a shared responsibility model across labs, enterprises, and hardware providers. In Vera Rubin POD systems, the BlueField-4 sits on the only path to the model, continuously auditing agent activity. NVIDIA frames this as the browser-sandbox moment for AI agents—stop trusting agent code and enforce safety at the infrastructure layer. OpenShell is available on GitHub now.

Why it matters: NVIDIA pushes agent safety to the silicon level with a concrete two-layer architecture — not a concept paper. The ding is that this is an NVIDIA developer blog with an incentive to promote their DPU hardware, and there's no third-party validation or cross-source discussion yet...