NVIDIA OpenShell Developer Guide
OpenShell is the safe, private runtime for fleets of autonomous AI agents. Run agents in sandboxed environments that protect your data, credentials, and infrastructure.
NVIDIA OpenShell is the safe, private runtime for fleets of 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
Section titled “Get Started”Install OpenShell and create your first sandbox in two commands.
curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/main/install.sh | shRefer to Run Your First Agent for the complete image, provider, and policy workflow.
Explore
Section titled “Explore”Learn about OpenShell and its capabilities.
ConceptPrepare an image, attach providers, and launch an agent in a sandbox.
TutorialHands-on walkthroughs from first sandbox to custom policies.
ConceptDeploy gateways, create sandboxes, configure policies, providers, and workload images for your AI agents.
ConceptAttach model providers to selected sandboxes and call their native endpoints without exposing credentials.
ConceptUnderstand sandbox logs, access them with the CLI and TUI, and export OCSF JSON records.
How-ToDefine filesystem, process, and network controls for sandbox workloads.
ReferenceEvery configurable security control, its default, and the risk of changing it.
ConceptWe are a Cloud Native Computing Foundation sandbox project.
Copyright OpenShell a Series of LF Projects, LLC
For website terms of use, trademark policy and other project policies please see lfprojects.org/policies/.