krishicks
f88b58192b
* fix(ocsf): keep the fallback event context feature-independent With test-support, the fallback EventContext carried a fake sandbox identity, so a binary built with that feature unified in, such as by cargo build --workspace --all-targets, attributed unbound events to a sandbox that does not exist. Producer tests no longer need it: the validator accepts top-level container on its own, and the builder conformance test uses an explicit sandbox context. Signed-off-by: Kris Hicks <khicks@nvidia.com> * test(ocsf): pin builder compile_fail doctests to the missing field The HTTP, Network, Process, and SSH type-state doctests built their EventContext from a struct literal, so a new EventContext field would also make them fail to compile and they would keep passing with the guard removed. Build the context with ctx::ctx() so the missing required field is the only compile error. Signed-off-by: Kris Hicks <khicks@nvidia.com> * refactor(ocsf): share setter macros with type-state builders The HTTP, Network, Process, and SSH builders carry a type-state parameter, so they hand-copied the activity, action, disposition, severity, status, and message setters that the shared macros generate for other builders. Let the macros take an optional state parameter and use them on all four, and route both SSH endpoint setters through one state transition. Signed-off-by: Kris Hicks <khicks@nvidia.com> * docs(ocsf): add type_uid to the Network Activity example OCSF 1.8.0 requires type_uid, so the example that follows the conformance claim failed validation as written. Signed-off-by: Kris Hicks <khicks@nvidia.com> * test(e2e): report the last exec error in the OCSF conformance test The test discarded the result of the exec that generates traffic, so when the exec failed, for example without python3 in the image, the test retried for a minute and then blamed the JSONL copy. Keep the latest exec error and include it in the missing-classes failure. Signed-off-by: Kris Hicks <khicks@nvidia.com> * test(e2e): read the sandbox id label from podman ps JSON Signed-off-by: Kris Hicks <khicks@nvidia.com> --------- Signed-off-by: Kris Hicks <khicks@nvidia.com>
Important
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.
For native Windows support through Microsoft MXC, see the Windows build and runtime guide for setup and current limitations.
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 repository coding conventions.
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.