NVIDIA has launched the Open Agent Safety Platform to help organizations keep AI agents within approved boundaries using software controls and hardware-based monitoring. The platform combines OpenShell and Sentry to isolate agents, enforce access policies, and independently stop agents that try to exceed their permissions. #NVIDIA #OpenAgentSafetyPlatform #OpenShell #Sentry #BlueField4 #VeraRubinPOD
Keypoints
- NVIDIA introduced an open platform for AI agent safety.
- OpenShell isolates agents and controls their access to files, networks, and processes.
- Sentry monitors agent activity from separate hardware using BlueField-4 DPUs.
- The system can quarantine agents that try to cross their software boundaries.
- Scale AI is using the reference design for mission-critical enterprise and government applications.
Read More: https://www.helpnetsecurity.com/2026/09/28/nvidia-open-agent-safety-platform/