NVIDIA/OpenShell
Summary
OpenShell is a secure runtime from NVIDIA for managing autonomous AI agents, providing kernel-level enforcement and formal verification to enforce policies safely.
View Cached Full Text
Cached at: 09/29/26, 03:28 PM
NVIDIA/OpenShell
Source: https://github.com/NVIDIA/OpenShell
New in OpenShell 0.1.x: a stable release cadence, new isolation primitives, an expanded extension surface, and new APIs. Read the 0.1.0 upgrade guide.
OpenShell is the safe, private runtime for fleets of autonomous AI agents. Agents are most useful when they can read files, install packages, call APIs, and use credentials. OpenShell gives them that capability without giving them unrestricted access to your data, secrets, or network. You declare what each agent can touch in a policy, and OpenShell enforces it.
How It Works
OpenShell governs what agents can do in two ways: it instruments the kernel to enforce policy on every file access, system call, and network connection at runtime, and it uses formal verification to check what a policy change would allow before it is applied.
- Kernel-level enforcement. Each agent runs in an isolated sandbox. Kernel controls confine which files it can access and which system calls it can make, and every network connection passes through a policy check before it leaves the sandbox. Agents never see real credentials; OpenShell adds them only to requests bound for approved endpoints.
- Formally verified policy changes. Before a policy change is approved, OpenShell uses formal verification to flag risky new access it would grant, such as reaching a new host with credentials or calling a new API method, so those changes wait for human review.
See Architecture for how the gateway, supervisor, and sandbox fit together.
Quickstart
You need Linux, macOS on Apple Silicon, or Windows with WSL 2 (experimental), plus Docker, Podman, or host virtualization. See the Support Matrix for details.
curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/main/install.sh | sh
openshell sandbox create --name demo
The installer sets up the CLI and a local gateway. The default sandbox image is minimal Ubuntu with no agent installed. To run a real agent, follow Run Your First Agent: it runs OpenCode against a free OpenRouter model and shows how to approve new access as the agent needs it.
Explore Further
- Sandboxes: images, runtimes, GPUs, and lifecycle.
- Policies: filesystem, network, and process rules, with the advisor and prover for reviewing changes.
- Providers: credentials that work only at approved endpoints, including inference.
- Gateways: the control plane for sandboxes, policy, and access.
- Kubernetes: deploy the gateway with Helm. Your CNI must enforce
NetworkPolicy. - Extensibility: middleware, interceptors, and compute drivers.
- Tutorials: step-by-step policy and agent walkthroughs.
- Prerelease and development builds: try an upcoming release or the latest commit on
main.
Agent Skills
Install the public OpenShell skills for your coding agent:
npx skills add NVIDIA/OpenShell
The skills teach your agent to drive the OpenShell CLI, write sandbox policies, and debug gateways and inference routing. They live in skills/ and work without an OpenShell source checkout.
SDKs
SDKs connect applications to an OpenShell gateway. They do not install the CLI. Use the same OpenShell release for the SDK and the gateway when possible.
| Language | Install | Docs |
|---|---|---|
| Python | uv add openshell | README |
| TypeScript | npm install @nvidia/openshell-sdk (GitHub Packages) | README |
| Go | go get github.com/NVIDIA/OpenShell/sdk/go@latest | README |
| Rust | cargo add openshell-sdk --git https://github.com/NVIDIA/OpenShell --tag <release-tag> | Installation and usage |
Community
- Questions and discussion: GitHub Discussions
- Bug reports and feature requests: GitHub Issues, using the issue templates
- Security vulnerabilities: follow SECURITY.md. Do not open a GitHub issue.
- Roadmap: OpenShell Roadmap and the RFC board
- Try it in the cloud: Brev Launchable
OpenShell is built agent-first: it is developed with the same agent-driven workflows it enables. See CONTRIBUTING.md for development setup and the contribution workflow, and AGENTS.md for the contributor agent skills and workflow chains.
Telemetry
OpenShell collects anonymous telemetry, limited to operational categories and counts, to help improve the project. It does not collect sandbox names, hostnames, file paths, prompts, credentials, provider or model names, or user content. To disable it, set OPENSHELL_TELEMETRY_ENABLED=false on the gateway, or server.telemetryEnabled=false for Helm installs. You can also compile telemetry out entirely. See Telemetry for details and the community telemetry reports for published usage trends.
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 “AS 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.
License
This project is licensed under the Apache License 2.0.
Similar Articles
How Autonomous AI Agents Become Secure by Design With NVIDIA OpenShell
NVIDIA launches OpenShell, a secure-by-design runtime for autonomous AI agents that isolates agent operations in sandboxes and enforces security policies at the system level rather than relying on behavioral prompts. The toolkit, part of NVIDIA Agent Toolkit, enables enterprises to run coding agents and agentic workflows with unified policy management and compliance oversight.
NVIDIA shipped OpenShell, an open source sandbox that gives local and open agents real runtime limits instead of prompt rules. Over 100 firms joined the safety stack. OpenAI did not.
NVIDIA has released OpenShell, an open source sandbox that provides runtime constraints for local and open AI agents instead of relying on prompt rules. Over 100 firms have joined the safety initiative, while OpenAI did not participate.
@ClementDelangue: From what we know (take with a grain of salt, we need much more transparency!), if @OpenAI had been running this on the…
NVIDIA introduces OpenShell, an open-source runtime for secure AI agent execution with kernel-level enforcement and formal verification to prevent unauthorized actions.
Nvidia Introduces OpenShell Reference Architecture for AI Agent Safety
Nvidia announced the OpenShell Reference Architecture, a framework for building, containing, observing, and enforcing safe AI agents across enterprise infrastructure and edge systems throughout the full agent lifecycle.
We tested NVIDIA's new OpenShell agent sandbox: it stopped poisoned setup scripts from leaking secrets, but auto-approval granted new hosts in 12/12 trials
NVIDIA's OpenShell sandbox effectively isolates AI agents from sensitive data using microVM and default-deny policies, but critical vulnerabilities like auto-approval allow unauthorized host connections in testing.