Open Agent Safety Platform
AssessPlatforms
Nvidia's platform for enforcing security controls around AI agents.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by security coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7The New Stack·9/28/2026securityNvidia Unveils Open Agent Safety Platform for AI Agent Sandboxing
Nvidia announced the Open Agent Safety Platform, combining the OpenShell agent runtime with the Sentry watchdog running on BlueField-4 DPUs. The system is designed to enforce deterministic policy controls, isolate agents in kernel-enforced sandboxes, and cut off network access if behavior becomes unsafe.