AITechRadarabout 1 hour ago
Nvidia launches Open Agent Safety Platform
4 min read
Nvidia unveiled its Open Agent Safety Platform to stop autonomous AI agents from escaping boundaries. It combines OpenShell, a software runtime boundary, and Sentry, a hardware watchdog on BlueField-4 DPUs that quarantines rogue agents in milliseconds. Over 100 customers including Anthropic, Microsoft and SpaceXAI have adopted the safeguards, following recent AI-led security incidents.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyNvidia
