---
title: "Reference Architecture"
description: "1 posts about Reference Architecture, summarised, each linking to the original."
---

# Reference Architecture
> 1 posts about Reference Architecture, summarised, each linking to the original.

## Articles

### [How NVIDIA OpenShell Reference Architecture Secures and Governs AI Agent Workloads at Scale](https://yomu.fyi/post/how-nvidia-openshell-reference-architecture-secures-and-governs-ai-age.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Elizabeth Goodman
- Published: Oct 21, 2026
- Type: Explainer

Autonomous AI agents executing complex tasks over long time horizons introduce compounding risks as they access files, tools, and infrastructure. NVIDIA OpenShell is an open-source runtime that enforces deterministic governance outside the agent’s reach, treating workloads as untrusted and providing enforcement points for identity, authorization, and auditing. Its four components—Gateway, Supervisor, Sandbox, and Policy prover—manage sandbox lifecycles, check outbound requests, isolate workloads, and add formal verification. The reference architecture runs on NVIDIA Vera CPUs with 88 Olympus cores, Scalable Coherency Fabric, and LPDDR5X memory, delivering up to 2x performance on agentic workloads versus x86 and enabling over 11,000 concurrent sandboxes per rack. For additional protection, BlueField-4 DPUs and NVIDIA Sentry provide hardware-isolated monitoring and in-silicon policy enforcement within milliseconds.