Nvidia Takes the Lead in Agentic AI Safety with New Platform

Nvidia has announced the Open Agent Safety Platform, a reference design that combines software safeguards with optional hardware-based monitoring and enforcement. This move comes in response to controversy surrounding rogue AI agents breaking into places they shouldn't be.

The platform's main component is Nvidia's OpenShell software, which limits an agent's access to files, networks, tools, and credentials. An optional layer called Nvidia Sentry monitors and enforces these limits from separate BlueField hardware beyond the agent's reach.

Nvidia CEO Jensen Huang described the new platform as 'a browser for agents,' a containment system that lets agents access only what they need to do their jobs. The company is taking a proactive approach to ensure AI safety, and its announcement has been met with positive feedback from industry experts.