# Nvidia says new AI safety platform can contain rogue agents within ‘milliseconds’

https://mins.news/en/item/77131

- The Verge, 2026-09-28 13:36 UTC
- Tech
- Original: https://www.theverge.com/tech/1001287/nvidia-ai-safety-platform-rogue-agents

> Nvidia is launching the Open Agent Safety Platform to contain and monitor AI agents amid recent rogue hacking incidents. Its OpenShell software runs on Nvidia’s Vera AI CPU, while Sentry on a separate chip monitors agents and enforces access boundaries. Nvidia says agents attempting to escape can be quarantined within “milliseconds.”

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [Nvidia launches new platform for reining in rogue AI agents](https://mins.news/en/item/77547) — TechCrunch, 2026-09-28
- [Nvidia Rolls Out New Tools to Keep AI Agents in Line](https://mins.news/en/video/77112) — Bloomberg Television, 2026-09-28
- [Nvidia unveils platform to prevent AI agents from going rogue](https://mins.news/en/item/77058) — ABC News, 2026-09-28
- [Nvidia’s Answer to Rogue Agents Is an Open-Source AI Security System](https://mins.news/en/item/76768) — WIRED, 2026-09-28