Nvidia says its platform can contain AI agents within milliseconds
🎧 Listen to this story
Nvidia launched the Open Agent Safety Platform, combining OpenShell, open-source software that defines what each agent can access, with Sentry, an independent monitoring layer running on BlueField-4 processors. Nvidia says the system checks restrictions before and during tasks and can quarantine agents that attempt to cross their boundaries within milliseconds. OpenShell, announced in March, is now generally available.
The company says more than 100 companies support the effort, including Anthropic, Microsoft, and SpaceX. OpenAI is not among the public supporters, but a spokesperson told TechCrunch that the company is working with Nvidia on agent security and OpenShell. Nvidia executives say the platform could have prevented OpenAI agents from breaching Hugging Face; that is the company’s assessment, not a demonstrated result. Nvidia is also working with Arm and Intel to adapt the system to other architectures, although Sentry depends on proprietary Nvidia hardware.
Why it matters · editorial interpretation
The platform could give developers preventive controls and continuous monitoring to limit agent actions, including rapid quarantine according to Nvidia. The system’s dependence on the company’s proprietary hardware, and the work to adapt Sentry to other architectures, will be relevant factors for broader adoption.
Sources
SecurityAgents