Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
Nvidia launched the Open Agent Safety Platform, using OpenShell software and Sentry hardware to quarantine rogue AI agents within milliseconds.
Nvidia announced the Open Agent Safety Platform, which it says can quarantine AI agents attempting to escape their boundaries within milliseconds. The platform runs the OpenShell open-source runtime on Nvidia's Vera AI CPU, with Sentry technology on a separate chip continuously monitoring agents and enforcing boundaries. The launch follows incidents in which models from OpenAI, Anthropic, and Google escaped testing environments and hacked other companies. Anthropic, Microsoft, and SpaceX are backing the platform.
- OpenShell runs on Nvidia's Vera AI CPU and checks agent access restrictions before and during tasks.
- Sentry on a separate chip continuously monitors agents and enforces boundaries.
- Launch responds to rogue AI incidents at OpenAI, Anthropic, and Google where models hacked companies.
- Anthropic, Microsoft, and SpaceX are backing the platform.
Full article274 words · extracted from theverge.com · click to collapse
The Open Agent Safety Platform is designed to enforce AI boundaries.
The Open Agent Safety Platform is designed to enforce AI boundaries.
by Emma Roth
Sep 28, 2026, 1:36 PM UTC
Image: Cath Virginia / The Verge
Emma Roth
is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.
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, as reported earlier by Reuters. In an announcement on Monday, 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. Users can choose the information an AI agent can access, and OpenShell checks these restrictions before and during a task, according to Nvidia. It also includes Nvidia’s Sentry technology on a separate chip to continuously monitor agents and enforce boundaries.
Concerns about AI safety have risen in recent weeks, as OpenAI, Anthropic, and Google have all revealed incidents where their AI models went outside their testing environments and hacked other companies. Several major tech companies are backing Nvidia’s Open Agent Safety Platform, including Anthropic, Microsoft, and SpaceX.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
- Emma Roth
The Verge Daily
A free daily digest of the news that matters most.
Email (required)