NVIDIA Unveils Open Agent Safety Platform for Secure AI Deployment

NVIDIA has introduced the Open Agent Safety Platform, an open software platform and reference system design to strengthen AI security from agent testing to deployment. The platform aims to provide full-stack governance and control across software and hardware, compute, and robotics systems that run agents.

The Open Agent Safety Platform consists of NVIDIA OpenShell open source software and the NVIDIA Sentry reference system design. OpenShell provides a secure runtime boundary that traces all actions and enforces policy as agents run on NVIDIA Vera CPUs. As open source software, OpenShell can be extended to work with third-party compute platforms.

Sentry adds an out-of-band watchdog that runs on NVIDIA BlueField-4 DPUs to continuously monitor agent behavior. Sentry quarantines agents that attempt to move outside their boundaries in milliseconds.

Industry leaders from across the AI ecosystem are joining NVIDIA to strengthen AI safety for every industry across the full stack of infrastructure, software, models, and robotics. Organizations such as Anthropic, Cisco, CrowdStrike, Dell Technologies, Figure, HPE, Hugging Face, JPMorganChase, Microsoft, Palantir, Palo Alto Networks, Perplexity, Red Hat, Salesforce, SAP, Scale AI, ServiceNow, and SpaceXAI are collaborating with NVIDIA to advance AI safety.