Nvidia launches platform to contain rogue AI agents

Nvidia CEO Jensen Huang unveiled the Open Agent Safety Platform, a combined software and hardware toolkit designed to keep AI agents from escaping their test environments. The platform pairs OpenShell, open source software controlling agent access, with Sentry, an independent monitoring system running on Nvidia's BlueField-4 data processing units. By placing Sentry on a separate processor, Nvidia says it can isolate and quarantine rogue agents within milliseconds. The release follows breaches involving AI models from Anthropic, Google, OpenAI, and Meta. Dozens of companies, including Anthropic, Microsoft, and Oracle, have signed on to support the platform.