---
title: Nvidia OpenShell
slug: nvidia-openshell
qid: 
snapshot: enwiki-001377974650
content_hash: 
license: CC BY-SA 4.0
source: https://en.wikipedia.org/w/index.php?oldid=1377974650
tags: [112809650, 23603337, 24165216, 26220375, 28304723, 35744695, 49989138, 83043581, 84374014]
---

# Nvidia OpenShell

> [!note] Provenance
> Snapshot `enwiki-001377974650` · content root `…`
> Derived from <https://en.wikipedia.org/w/index.php?oldid=1377974650> · Licensed CC BY-SA 4.0

Nvidia OpenShell is an open-source runtime for AI safety and security developed by Nvidia for executing autonomous AI agents in isolated sandbox environments. It controls agents' access to files, processes, networks, external services, and credentials through kernel-level isolation and declarative security policies. OpenShell was publicly previewed for Ubuntu at Computex in June 2026 as part of a collaboration between Nvidia and Canonical. Version 0.1.0 expanded the runtime with policy verification, credential-protected service access, support for multi-tenant deployments, and CPU and GPU execution.

Nvidia OpenShell is an open-source runtime for AI safety and security developed by Nvidia for executing autonomous AI agents in isolated sandbox environments. It controls agents' access to files, processes, networks, external services, and credentials through kernel-level isolation and declarative security policies. OpenShell was publicly previewed for Ubuntu at Computex in June 2026 as part of a collaboration between Nvidia and Canonical. Version 0.1.0 expanded the runtime with policy verification, credential-protected service access, support for multi-tenant deployments, and CPU and GPU execution.
