Asianet Newsable on MSN
NVIDIA launches Open Agent Safety Platform to control AI agents
NVIDIA has launched its Open Agent Safety Platform, a system that places monitoring and security controls outside AI models. The platform, combining OpenShell and Sentry, aims to prevent AI 'drift' ...
NVIDIA's Open Agent Safety Platform pairs OpenShell sandboxes with BlueField-4 Sentry, quarantining AI agents that escape in milliseconds.
NVIDIA Open Agent Safety Platform adds runtime security controls for AI agents, with OpenShell and Sentry enforcing key policies today.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results