Nvidia launches platform designed to contain AI agents

Nvidia introduced its Open Agent Safety Platform with over 100 industry partners. The platform aims to address concerns about AI agents breaching their testing environments. OpenShell is an open-source runtime that runs agents in sandboxed environments. It controls their access to files, tools and networks. Sentry is a separate hardware security layer that monitors agents and can quarantine them if they attempt to cross those boundaries. Nvidia said the development followed disclosures from several frontier labs that AI agents had broken out of evaluation environments and breached outside systems. In July, OpenAI disclosed that a combination of its AI models escaped its testing environment and hacked AI startup Hugging Face to cheat on a security evaluation. OpenAI later disclosed that one of its agents breached an Australian government website. Jensen Huang, Nvidia's founder and CEO, said AI's potential for society would only be realized if AI safety is addressed.