For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
  • About NVIDIA OpenShell
    • Overview
    • How It Works
    • Installation
    • Container Gateway
    • Supported Agents
    • Release Notes
  • Get Started
    • Quickstart
    • Tutorials
  • Manage OpenShell
    • Sandboxes
    • Gateways
    • Providers
    • Providers v2
    • Policies
    • Policy Advisor
    • Inference Routing
  • Observability
    • Accessing Logs
    • Logging
    • OCSF JSON Export
  • Kubernetes
    • Setup
    • Managing Certificates
    • Ingress
    • Access Control
    • OpenShift
  • Reference
    • Gateway Auth
    • Default Policy
    • Policy Schema
    • Compute Drivers
    • Gateway Config
    • Support Matrix
  • Security
    • Security Best Practices
  • Resources
    • License
NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright Β© 2026, NVIDIA Corporation.

LogoLogoOpenShell
On this page
  • Get Started
  • Explore

NVIDIA OpenShell Developer Guide

||View as Markdown|
Previous

License

GitHubLicensePyPI

NVIDIA OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments that protect your data, credentials, and infrastructure. Agents run with exactly the permissions they need and nothing more, governed by declarative policies that prevent unauthorized file access, data exfiltration, and uncontrolled network activity.

Get Started

Install OpenShell and create your first sandbox in two commands.

$ curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/main/install.sh | sh
$ openshell sandbox create -- claude-- opencode-- codex

Refer to the Quickstart for more details.


Explore

About OpenShell

Learn about OpenShell and its capabilities.

Concept
Quickstart

Install OpenShell and create your first sandbox in two commands.

Tutorial
Tutorials

Hands-on walkthroughs from first sandbox to custom policies.

Concept
Gateways and Sandboxes

Deploy gateways, create sandboxes, configure policies, providers, and community images for your AI agents.

Concept
Inference Routing

Keep inference traffic private by routing API calls to local or self-hosted backends.

Concept
Observability

Understand sandbox logs, access them with the CLI and TUI, and export OCSF JSON records.

How-To
Reference

Policy schema, environment variables, and default policy details.

Reference
Security Best Practices

Every configurable security control, its default, and the risk of changing it.

Concept

Notice and Disclaimer

This software automatically retrieves, accesses or interacts with external materials. Those retrieved materials are not distributed with this software and are governed solely by separate terms, conditions and licenses. You are solely responsible for finding, reviewing and complying with all applicable terms, conditions, and licenses, and for verifying the security, integrity and suitability of any retrieved materials for your specific use case. This software is provided β€œAS IS”, without warranty of any kind. The author makes no representations or warranties regarding any retrieved materials, and assumes no liability for any losses, damages, liabilities or legal consequences from your use or inability to use this software or any retrieved materials. Use this software and the retrieved materials at your own risk.