Red Hat and NVIDIA Expand AI Agent Security Partnership
Oct 21, 2026
Cybersecurity
NVIDIA Introduces Hardware Backed Agent Safety Platform
Sep 28, 2026
NVIDIA's Open Agent Safety Platform combines a sandboxed runtime with independent monitoring and policy enforcement on BlueField hardware.
NVIDIA introduces the Open Agent Safety Platform, a reference design for monitoring and controlling AI agents, as detailed in a company blog post. The platform combines OpenShell on NVIDIA Vera CPUs with NVIDIA Sentry on BlueField-4 data processing units.
OpenShell is an open source runtime that places agents in isolated sandboxes. Operators can define which files, networks, tools, processes, and credentials an agent may access, then verify and enforce those limits while the agent runs.
NVIDIA Sentry adds an independent monitoring and enforcement layer using BlueField hardware and NVIDIA DOCA. In Vera Rubin POD systems, BlueField-4 sits on the node's path to the model, where it can record agent activity and enforce policies in real time without giving the agent access to those controls. The platform also supports other hardware systems.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly, AI Policy Brief or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 13 German military grounds Quantum Systems drones after malware hits update server Nov 13 ENISA: frontier AI models found 220 potential security flaws in EU institutions' open-source code Nov 12 US Army criminal investigators seek AI tools to monitor darknet and encrypted messaging Nov 12 OpenAI launches Daybreak Red Team and Defense Factory security agents Nov 12 OpenAI says automated red teaming made GPT-6 Astra harder to jailbreakMore from AI Safety
Nov 12 MIT-led team catalogs 2,206 proposed AI safeguards and finds gaps in agent oversight Nov 12 OpenAI says automated red teaming made GPT-6 Astra harder to jailbreak Nov 12 OpenAI signs Paris charter on children's AI safety and gives $2 million to research Nov 12 Norway and the UK agree to cooperate on AI safety, compute and defence uses Nov 12 Japan considers binding orders and penalties for AI firms over safety risksFree newsletter
Cybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
NVIDIA Partners Expand European AI Clouds and Agent Controls
Oct 21, 2026
AI Agents
Supermicro Introduces 256 CPU NVIDIA Vera Rack for AI Agents
Oct 23, 2026
Data Centers
ServiceNow Expands NVIDIA Partnership for AI Agent Security
Oct 21, 2026
Enterprise
NVIDIA Commits $250 Million in Compute to UK AI Safety Research
Oct 14, 2026
AI Safety
NVIDIA Adds Confidential Bare Metal for Sensitive AI Workloads
Oct 22, 2026
Cybersecurity
Free, six days a week
Daily AI Brief: the AI news that matters, in your inbox.