# Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’ > Source: > Published: 2026-09-28 13:36:06+00:00 # Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’ By Emma RothSource: [The Verge AI](https://www.theverge.com) [Nvidia](https://www.machinebrief.com/glossary/nvidia) is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a [wave of rogue hacking incidents](http://theverge.com/ai-artificial-intelligence/1000644/irregular-rogue-ai-cyberattacks-hacking-openai-meta-anthropic-google), as [reported earlier by *Reuters*](https://www.reuters.com/legal/litigation/nvidia-releases-ai-safety-software-it-says-could-have-stopped-hugging-face-hack-2026-09-28/). In [an announcement on Monday](https://nvidianews.nvidia.com/news/open-agent-safety-platform), Nvidia says its new Open Agent Safety Platform can quarantine agents that attempt to escape their boundaries within "milliseconds." The platform uses Nvidia's OpenShell open-source software, which runs on the company's [Vera AI CPU](https://nvidianews.nvidia.com/news/nvidia-unveils-vera-the-cpu-for-agents). Users can choose the information an [AI agent](https://www.machinebrief.com/glossary/ai-agent) can access, and OpenShell checks these restrictions before and during a task, [according to Nvidia](https://developer.nvidia.com/blog/nvidia-open-agent-safety-platform-a-reference-for-continuous-in-silicon-agent-monitoring/). It also includes Nvidia's Sentry technology on a separate … Get AI news in your inbox Daily digest of what matters in AI.