How Autonomous AI Agents Become Secure by Design With NVIDIA OpenShell
Source: NVIDIA AI Blog
Introducing OpenShell for Secure Autonomous Agents
Autonomous agents mark a new inflection point in AI. Systems are no longer limited to generating responses or reasoning through tasks—they can take action. Agents can read files, use tools, write and run code, and execute workflows across enterprise systems, all while expanding their own capabilities.
Application‑layer risk grows exponentially when agents continuously improve and evolve. The NVIDIA OpenShell runtime is being built to address this challenge.
Part of the NVIDIA Agent Toolkit, OpenShell is an open‑source, secure‑by‑design runtime for running autonomous agents such as claws. It ensures each agent runs inside its own sandbox, separating application‑layer operations from infrastructure‑layer policy enforcement.
- Security policies are applied at the system level, out of reach of the agent.
- OpenShell enforces constraints on the environment, preventing agents from overriding policies or leaking credentials or private data, even if compromised.
With OpenShell, enterprises can separate agent behavior, policy definition, and policy enforcement. Organizations gain a single, unified policy layer to define and monitor how autonomous systems operate. Coding agents, research assistants, and agentic workflows all run under the same runtime policies regardless of host operating system, simplifying compliance and operational oversight.
This is the “browser tab” model applied to agents: sessions are isolated, resources are controlled, and permissions are verified by the runtime before any action takes place.
Securing autonomous systems requires an integrated ecosystem. OpenShell adds privacy and security controls for AI agents, and NVIDIA is collaborating with security partners—including Cisco, CrowdStrike, Google Cloud, Microsoft Security, and TrendAI—to align runtime policy management and enforcement across the enterprise stack.
OpenShell Provides an Enterprise‑Grade Sandbox for Building Personal AI Assistants
NVIDIA NemoClaw is an open‑source reference stack that simplifies installing OpenClaw always‑on assistants with the OpenShell runtime and NVIDIA Nemotron models in a single command.
NemoClaw offers enthusiasts an open reference for building self‑evolving personal AI agents (claws). Because security needs vary, NemoClaw includes a reference example for policy‑based privacy and security guardrails, giving users more control over their agents’ behavior and data handling. Users can customize it for specific use cases—much like adjusting security preferences for applications on a phone.
Key points
- NemoClaw includes an example OpenShell configuration that defines how the agent should interact with systems.
- It uses open‑source models like NVIDIA Nemotron alongside OpenShell.
- The setup enables self‑evolving claws to run securely in clouds, on‑premises, or on personal computers, including NVIDIA GeForce RTX PCs and laptops, NVIDIA RTX PRO‑powered workstations, as well as NVIDIA DGX Station and NVIDIA DGX Spark AI supercomputers.
Both OpenShell and NemoClaw are in early preview. NVIDIA is building in the open with the community and its partners to enable enterprises to scale self‑evolving, long‑running autonomous agents safely, confidently, and in compliance with global security standards.
Get started
- NVIDIA OpenShell: http://build.nvidia.com/OpenShell
- Launch a ready‑to‑use environment on NVIDIA Brev: https://brev.nvidia.com/launchable/deploy/now?gpu=H200&launchableID=env-3AaK9NmCzWp3pVyUDNNFBt805FT
- Explore the open‑source project on GitHub: https://github.com/nvidia/openshell