NVIDIA OpenShell#

GitHub License PyPI

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 the CLI and create your first sandbox in two commands.

$ uv tool install -U openshell
$ openshell sandbox create -- claude--from openclaw-- opencode-- codex

Refer to the Quickstart for more details.


Explore#

About OpenShell

Learn about OpenShell and its capabilities.

Overview of NVIDIA OpenShell
Quickstart

Install the CLI and create your first sandbox in two commands.

Quickstart
Tutorials

Hands-on walkthroughs from first sandbox to custom policies.

Tutorials
Gateways and Sandboxes

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

Deploy and Manage Gateways
Inference Routing

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

About Inference Routing
Reference

Policy schema, environment variables, and system architecture.

Default Policy Reference