CERT24Nvidia unveils AI-agent safety platform with hardware-based watchdogLoading data…
CERT24Threat Observatory
Period

Nvidia unveils AI-agent safety platform with hardware-based watchdog

Nvidia announced the Open Agent Safety Platform, which combines open source software and a reference system design to keep AI agents within defined boundaries from testing through deployment. Its main components are OpenShell, which sandboxes agents and enforces policy, and Sentry, a watchdog that runs separately on Nvidia BlueField-4 DPUs.

← Back to intelligence

Nvidia unveils AI-agent safety platform with hardware-based watchdog

Nvidia announced the Open Agent Safety Platform, which combines open source software and a reference system design to keep AI agents within defined boundaries from testing through deployment. Its main components are OpenShell, which sandboxes agents and enforces policy, and Sentry, a watchdog that runs separately on Nvidia BlueField-4 DPUs.