NVIDIA OpenShell
OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments that protect your data, credentials, and infrastructure — governed by declarative YAML policies that prevent unauthorized file access, data exfiltration, and uncontrolled network activity.
OpenShell is built agent-first. The project ships with agent skills for everything from gateway troubleshooting to policy generation, and we expect contributors to use them.
Alpha software — single-player mode. OpenShell is proof-of-life: one developer, one environment, one gateway. We are building toward multi-tenant enterprise deployments, but the starting point is getting your own environment up and running. Expect rough edges. Bring your agent.
Quickstart
Prerequisites
- A supported host — macOS, Windows with WSL 2, or Linux.
- A local runtime — Docker, Podman, or host virtualization enabled for MicroVM-backed sandboxes.
Install
Binary (recommended):
curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/main/install.sh | sh
From PyPI (requires uv):
uv tool install -U openshell
Both methods install the latest stable release by default. To install a specific version, set OPENSHELL_VERSION for the binary installer or pin the version with uv tool install openshell==<version>.
Helm chart:
Experimental — the Kubernetes deployment path is under active development. Expect rough edges and breaking changes.
Deploy the OpenShell gateway into a Kubernetes cluster from the OCI chart published to GHCR:
helm install openshell oci://ghcr.io/nvidia/openshell/helm-chart
See deploy/helm/openshell/README.md for available versions and configuration.
For deploying OpenShell on OpenShift, see deploy/helm/openshell/README.md#install-on-openshift.
Manual gateway binary:
Use this when you want to run the gateway directly instead of installing a package-managed service. Choose a release tag from OpenShell GitHub Releases, then download the gateway artifact for your host:
| Host | GATEWAY_TARGET |
|---|---|
| Linux x86_64 | x86_64-unknown-linux-gnu |
| Linux Arm64 | aarch64-unknown-linux-gnu |
| macOS Apple Silicon | aarch64-apple-darwin |
VERSION="v0.0.0"
GATEWAY_TARGET="x86_64-unknown-linux-gnu"
BASE_URL="https://github.com/NVIDIA/OpenShell/releases/download/${VERSION}"
mkdir -p "$HOME/.local/bin"
curl -LsSf "${BASE_URL}/openshell-gateway-${GATEWAY_TARGET}.tar.gz" | tar -xz -C "$HOME/.local/bin" openshell-gateway
chmod 755 "$HOME/.local/bin/openshell-gateway"
export PATH="$HOME/.local/bin:$PATH"
Generate local mTLS materials for the gateway:
export OPENSHELL_STATE_DIR="${XDG_STATE_HOME:-$HOME/.local/state}/openshell"
export OPENSHELL_TLS_DIR="${OPENSHELL_STATE_DIR}/tls"
mkdir -p "${OPENSHELL_STATE_DIR}/gateway"
openshell-gateway generate-certs \
--output-dir "${OPENSHELL_TLS_DIR}" \
--server-san host.openshell.internal
Configure the gateway environment before starting it:
| Variable | Value | Purpose |
|---|---|---|
OPENSHELL_BIND_ADDRESS |
127.0.0.1 |
Listen on loopback for a local gateway. |
OPENSHELL_SERVER_PORT |
17670 |
Gateway API and SSH proxy port. |
OPENSHELL_TLS_CERT |
${OPENSHELL_TLS_DIR}/server/tls.crt |
Server certificate generated by generate-certs. |
OPENSHELL_TLS_KEY |
${OPENSHELL_TLS_DIR}/server/tls.key |
Server private key generated by generate-certs. |
OPENSHELL_TLS_CLIENT_CA |
${OPENSHELL_TLS_DIR}/ca.crt |
CA used to verify mTLS clients. |
OPENSHELL_DB_URL |
sqlite:${OPENSHELL_STATE_DIR}/gateway/openshell.db |
Gateway state database. |
OPENSHELL_GRPC_ENDPOINT |
https://127.0.0.1:${OPENSHELL_SERVER_PORT} |
Callback endpoint exposed to sandbox supervisors. |
OPENSHELL_SSH_GATEWAY_HOST |
127.0.0.1 |
Hostname advertised for SSH proxy connections. |
OPENSHELL_SSH_GATEWAY_PORT |
${OPENSHELL_SERVER_PORT} |
Port advertised for SSH proxy connections. |
OPENSHELL_SSH_HANDSHAKE_SECRET |
output of openssl rand -hex 32 |
Shared secret for gateway-to-sandbox SSH handshakes. Persist this value across restarts. |
OPENSHELL_DRIVERS |
docker or podman |
Compute driver used to launch sandbox containers. |
OPENSHELL_SANDBOX_IMAGE |
ghcr.io/nvidia/openshell-community/sandboxes/base:latest |
Default sandbox image. |
OPENSHELL_DOCKER_TLS_CA |
${OPENSHELL_TLS_DIR}/ca.crt |
Docker driver CA mounted into sandboxes. |
OPENSHELL_DOCKER_TLS_CERT |
${OPENSHELL_TLS_DIR}/client/tls.crt |
Docker driver client certificate mounted into sandboxes. |
OPENSHELL_DOCKER_TLS_KEY |
${OPENSHELL_TLS_DIR}/client/tls.key |
Docker driver client key mounted into sandboxes. |
OPENSHELL_SUPERVISOR_IMAGE |
ghcr.io/nvidia/openshell/supervisor:${VERSION#v} |
Podman driver supervisor image. |
OPENSHELL_PODMAN_TLS_CA |
${OPENSHELL_TLS_DIR}/ca.crt |
Podman driver CA mounted into sandboxes. |
OPENSHELL_PODMAN_TLS_CERT |
${OPENSHELL_TLS_DIR}/client/tls.crt |
Podman driver client certificate mounted into sandboxes. |
OPENSHELL_PODMAN_TLS_KEY |
${OPENSHELL_TLS_DIR}/client/tls.key |
Podman driver client key mounted into sandboxes. |
For Docker, set the Docker TLS variables. For Podman, enable the user socket with systemctl --user enable --now podman.socket, set OPENSHELL_DRIVERS=podman, and set the Podman TLS variables.
Start the gateway in the foreground:
openshell-gateway
Create a sandbox
openshell sandbox create -- claude # or opencode, codex, copilot
The sandbox container includes the following tools by default:
| Category | Tools |
|---|---|
| Agent | claude, opencode, codex, copilot |
| Language | python (3.13), node (22) |
| Developer | gh, git, vim, nano |
| Networking | ping, dig, nslookup, nc, traceroute, netstat |
For more details see https://github.com/NVIDIA/OpenShell-Community/tree/main/sandboxes/base.
See network policy in action
Every sandbox starts with minimal outbound access. You open additional access with a short YAML policy that the proxy enforces at the HTTP method and path level, without restarting anything.
# 1. Create a sandbox (starts with minimal outbound access)
openshell sandbox create
# 2. Inside the sandbox — blocked
sandbox$ curl -sS https://api.github.com/zen
curl: (56) Received HTTP code 403 from proxy after CONNECT
# 3. Back on the host — apply a read-only GitHub API policy
sandbox$ exit
openshell policy set demo --policy examples/sandbox-policy-quickstart/policy.yaml --wait
# 4. Reconnect — GET allowed, POST blocked by L7
openshell sandbox connect demo
sandbox$ curl -sS https://api.github.com/zen
Anything added dilutes everything else.
sandbox$ curl -sS -X POST https://api.github.com/repos/octocat/hello-world/issues -d '{"title":"oops"}'
{"error":"policy_denied","detail":"POST /repos/octocat/hello-world/issues not permitted by policy"}
See the full walkthrough or run the automated demo:
bash examples/sandbox-policy-quickstart/demo.sh
How It Works
OpenShell isolates each sandbox in its own container with policy-enforced egress routing. A lightweight gateway coordinates sandbox lifecycle, and every outbound connection is intercepted by the policy engine, which does one of three things:
- Allows — the destination and binary match a policy block.
- Routes for inference — strips caller credentials, injects backend credentials, and forwards to the managed model.
- Denies — blocks the request and logs it.
| Component | Role |
|---|---|
| Gateway | Control-plane API that coordinates sandbox lifecycle and acts as the auth boundary. |
| Sandbox | Isolated runtime with container supervision and policy-enforced egress routing. |
| Policy Engine | Enforces filesystem, network, and process constraints from application layer down to kernel. |
| Privacy Router | Privacy-aware LLM routing that keeps sensitive context on sandbox compute. |
OpenShell runs a gateway control plane that manages sandbox lifecycle through a configured compute driver. Supported compute platforms include Docker, Podman, MicroVM, and Kubernetes.
Protection Layers
OpenShell applies defense in depth across four policy domains:
| Layer | What it protects | When it applies |
|---|---|---|
| Filesystem | Prevents reads/writes outside allowed paths. | Locked at sandbox creation. |
| Network | Blocks unauthorized outbound connections. | Hot-reloadable at runtime. |
| Process | Blocks privilege escalation and dangerous syscalls. | Locked at sandbox creation. |
| Inference | Reroutes model API calls to controlled backends. | Hot-reloadable at runtime. |
Policies are declarative YAML files. Static sections (filesystem, process) are locked at creation; dynamic sections (network, inference) can be hot-reloaded on a running sandbox with openshell policy set.
Providers
Agents need credentials — API keys, tokens, service accounts. OpenShell manages these as providers: named credential bundles that are injected into sandboxes at creation. The CLI auto-discovers credentials for recognized agents (Claude, Codex, OpenCode, Copilot) from your shell environment, or you can create providers explicitly with openshell provider create. Credentials never leak into the sandbox filesystem; they are injected as environment variables at runtime.
GPU Support (Experimental)
Experimental — GPU passthrough works on supported hosts but is under active development. Expect rough edges and breaking changes.
OpenShell can pass host GPUs into sandboxes for local inference, fine-tuning, or any GPU workload. Add --gpu when creating a sandbox:
openshell sandbox create --gpu --from [gpu-enabled-sandbox] -- claude
Docker-backed GPU sandboxes auto-select CDI when available and otherwise fall back to Docker's NVIDIA GPU request path (--gpus all). GPU intent is also inferred automatically for community images with gpu in the name.
Requirements: NVIDIA drivers and the NVIDIA Container Toolkit must be installed on the host. The sandbox image itself must include the appropriate GPU drivers and libraries for your workload — the default base image does not. See the BYOC example for building a custom sandbox image with GPU support.
Supported Agents
| Agent | Source | Notes |
|---|---|---|
| Claude Code | base |
Works out of the box. Provider uses ANTHROPIC_API_KEY. |
| OpenCode | base |
Works out of the box. Provider uses OPENAI_API_KEY or OPENROUTER_API_KEY. |
| Codex | base |
Works out of the box. Provider uses OPENAI_API_KEY. |
| GitHub Copilot CLI | base |
Works out of the box. Provider uses GITHUB_TOKEN or COPILOT_GITHUB_TOKEN. |
| OpenClaw | Community | Launch with openshell sandbox create --from openclaw. |
| Ollama | Community | Launch with openshell sandbox create --from ollama. |
Key Commands
| Command | Description |
|---|---|
openshell sandbox create -- <agent> |
Create a sandbox and launch an agent. |
openshell sandbox connect [name] |
SSH into a running sandbox. |
openshell sandbox list |
List all sandboxes. |
openshell provider create --type [type]] --from-existing |
Create a credential provider from env vars. |
openshell policy set <name> --policy file.yaml |
Apply or update a policy on a running sandbox. |
openshell policy get <name> |
Show the active policy. |
openshell inference set --provider <p> --model <m> |
Configure the inference.local endpoint. |
openshell logs [name] --tail |
Stream sandbox logs. |
openshell term |
Launch the real-time terminal UI for debugging. |
See the full documentation for command guides, tutorials, and reference material.
Terminal UI
OpenShell includes a real-time terminal dashboard for monitoring gateways, sandboxes, and providers — inspired by k9s.
openshell term
The TUI gives you a live, keyboard-driven view of your gateway and sandboxes. Navigate with Tab to switch panels, j/k to move through lists, Enter to select, and : for command mode. Gateway health and sandbox status auto-refresh every two seconds.
Community Sandboxes and BYOC
Use --from to create sandboxes from the OpenShell Community catalog, a local directory, or a container image:
openshell sandbox create --from openclaw # community catalog
openshell sandbox create --from ./my-sandbox-dir # local Dockerfile
openshell sandbox create --from registry.io/img:v1 # container image
See the community sandboxes catalog and the BYOC example for details.
Explore with Your Agent
Clone the repo and point your coding agent at it. The project includes agent skills that can answer questions, walk you through workflows, and diagnose problems — no issue filing required.
git clone https://github.com/NVIDIA/OpenShell.git # or git@github.com:NVIDIA/OpenShell.git
cd OpenShell
# Point your agent here — it will discover the skills in .agents/skills/ automatically
Your agent can load skills for CLI usage (openshell-cli), gateway troubleshooting (debug-openshell-cluster), inference troubleshooting (debug-inference), policy generation (generate-sandbox-policy), and more. See CONTRIBUTING.md for the full skills table.
Built With Agents
OpenShell is developed using the same agent-driven workflows it enables. The .agents/skills/ directory contains workflow automation that powers the project's development cycle:
- Spike and build: Investigate a problem with
create-spike, then implement it withbuild-from-issueonce a human approves. - Triage and route: Community issues are assessed with
triage-issue, classified, and routed into the spike-build pipeline. - Security review:
review-security-issueproduces a severity assessment and remediation plan.fix-security-issueimplements it. - Policy authoring:
generate-sandbox-policycreates YAML policies from plain-language requirements or API documentation.
All implementation work is human-gated — agents propose plans, humans approve, agents build. See AGENTS.md for the full workflow chain documentation.
Getting Help
- Questions and discussion: GitHub Discussions
- Bug reports: GitHub Issues — use the bug report template
- Security vulnerabilities: See SECURITY.md — do not use GitHub Issues
- Agent-assisted help: Clone the repo and use the agent skills in
.agents/skills/for self-service diagnostics
Learn More
- Full Documentation — overview, architecture, tutorials, and reference
- Quickstart — detailed install and first sandbox walkthrough
- GitHub Sandbox Tutorial — end-to-end scoped GitHub repo access
- Architecture — detailed architecture docs and design decisions
- Roadmap — planned work and project priorities
- Support Matrix — platforms, versions, and kernel requirements
- Brev Launchable — try OpenShell on cloud compute without local setup
- Agent Instructions — system prompt and workflow documentation for agent contributors
Contributing
OpenShell is built agent-first — your agent is your first collaborator. Before opening issues or submitting code, point your agent at the repo and let it use the skills in .agents/skills/ to investigate, diagnose, and prototype. See CONTRIBUTING.md for the full agent skills table, contribution workflow, and development setup.
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.