Nvidia launches Open Agent Safety Platform to physically restrain rogue AI agents
Hardware-enforced sandboxing uses BlueField units to quarantine autonomous agents

Nvidia has launched the Open Agent Safety Platform, combining its OpenShell sandboxing environment with BlueField-powered Sentry hardware. The setup is designed to continuously monitor autonomous AI agents and isolate systems exhibiting unwanted or hazardous behaviours. By incorporating hardware-level controls, the platform offers data centre operators an enforceable containment mechanism for agentic deployments.
Original source
This summary was written by the GPU Data Hub desk from reporting published by Tom's Hardware on 1 Oct 2026, 14:30. Read the full article at the original publisher.
Read Original Source →Companies