Nvidia Launches Scale-In to Secure Agentic AI Factories
Nvidia has unveiled Scale-In, a new networking infrastructure pillar designed to secure and manage agentic AI factories. Powered by BlueField-4, DOCA software, and Spectrum-X Ethernet, Scale-In provides in-silicon security engines that monitor agents out-of-band across memory, storage, GPUs, and CPUs. Since August, Nvidia has expanded its agent security strategy with the Open Agent Safety Platform, combining OpenShell with Nvidia Sentry for hardware-based enforcement. An October update added the OpenShell Reference Architecture, integrating Vera Rubin infrastructure and BlueField-4 to support secure agent execution across enterprise systems.
