POLICY · COMPANIES · #1127
NVIDIA publishes OpenShell and Open Agent Safety Platform for continuous in-silicon agent monitoring
NVIDIA introduced OpenShell, an Apache-2.0 open-source secure runtime for sandboxed autonomous AI agents, and described the NVIDIA Open Agent Safety Platform that pairs OpenShell on Vera CPUs with NVIDIA Sentry on BlueField-4 DPUs to provide layered, out-of-band monitoring and real-time policy enforcement. The platform emphasizes verifiable policies, out-of-band enforcement, controlling the path to the model, scaling agent authority with reasoning visibility, and a shared responsibility model across labs, enterprises, and hardware providers.
KEY POINTS
- NVIDIA introduced OpenShell, an Apache-2.0 open-source secure runtime for sandboxed autonomous AI agents, and described the NVIDIA Open Agent Safety Platform that pairs OpenShell on Vera CPUs with NVIDIA Sentry on BlueField-4 DPUs to provide layered, out-of-band monitoring and real-time policy enforcement.
- The platform emphasizes verifiable policies, out-of-band enforcement, controlling the path to the model, scaling agent authority with reasoning visibility, and a shared responsibility model across labs, enterprises, and hardware providers.
- This combines open-source runtime isolation with hardware-based out-of-band enforcement on NVIDIA CPUs and DPUs, creating a practical layer for monitoring and enforcing agent behavior that could materially affect how organizations deploy agentic AI safely.
WHY IT MATTERS
This combines open-source runtime isolation with hardware-based out-of-band enforcement on NVIDIA CPUs and DPUs, creating a practical layer for monitoring and enforcing agent behavior that could materially affect how organizations deploy agentic AI safely.