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 — Linux, macOS (Apple Silicon), or Windows with WSL 2 (experimental).
• 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 (binary) or pin the version with uv tool install openshell==<version>. A dev release is also available that tracks the latest commit on main.

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, dev tag conventions, and configuration.

For deploying OpenShell on OpenShift, see deploy/helm/openshell/README.md#install-on-openshift.

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 (3.14), 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).

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	NemoClaw	Run OpenClaw more securely inside NVIDIA OpenShell with managed inference using NemoClaw.
Hermes Agent	NemoClaw	Run Hermes Agent more securely inside NVIDIA OpenShell with managed inference using NemoClaw.
Ollama	Community	Launch with openshell sandbox create --from ollama.
Pi	Community	Launch with openshell sandbox create --from pi.

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 gemini             # community catalog
openshell sandbox create --from ./my-sandbox-dir   # local Dockerfile
openshell sandbox create --from registry.io/img:v1 # container image

See the OpenShell Community 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; a human accepts it with state:accepted or roadmap placement, or declines it. Accepted work can remain human-owned or enter the optional, human-gated agent:* planning and implementation workflow.
• Triage and route: Community issues are assessed with triage-issue. Agents establish technical validity and impact; humans decide whether the project should act and where the work sits on the roadmap.
• Security review: review-security-issue produces a severity assessment and remediation plan. fix-security-issue implements it.
• Policy authoring: generate-sandbox-policy creates YAML policies from plain-language requirements or API documentation.

All agent implementation work is human-gated: maintainers explicitly request a plan, agents propose it, maintainers approve it, and 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
• RFC Board — RFC proposals tracked on the OpenShell Roadmap with the rfc label
• 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. Issues should include a user story, problem statement, impact, and acceptance criteria. The impact should explain the consequences of the current behavior and why existing workarounds are insufficient. Feature requests also require a workflow-level proposed design and alternatives; bug reports add reproduction steps, environment details, and relevant logs. Once maintainers accept work, contributors should use the skills in .agents/skills/ to investigate the current code and behavior, implement the change, and verify it. If an issue contains earlier diagnostics, verify them rather than relying on them. See CONTRIBUTING.md for the full agent skills table, contribution workflow, and development setup.

Telemetry

OpenShell collects anonymous telemetry to help improve the project for developers. This data is not used to track individual user behavior. It helps us understand aggregate usage of sandbox, provider, and policy workflows so we can prioritize product improvements and share usage trends with the community.

Disable telemetry at runtime by setting OPENSHELL_TELEMETRY_ENABLED=false on the gateway deployment. For Helm installs, set server.telemetryEnabled=false. OpenShell propagates this deployment setting into sandbox supervisor environments so sandbox-side telemetry collection is disabled as well.

You can also compile telemetry out entirely. Telemetry support is a default-on telemetry Cargo feature; building with --no-default-features produces binaries that contain no telemetry endpoint, no telemetry HTTP client, and no emission code. Build telemetry-free artifacts with, for example, cargo build --release -p openshell-server --no-default-features (gateway) and the equivalent for openshell-sandbox and openshell-driver-vm. With telemetry compiled out, the gateway emits nothing and reports telemetry disabled to the sandboxes it launches.

Telemetry events are limited to anonymous operational categories and counts, such as sandbox lifecycle outcomes, provider profile buckets, policy decision counts, and aggregate network activity denial categories. OpenShell telemetry does not collect sandbox names or IDs, hostnames, file paths, binary paths, prompts, credentials, provider names, model names, or user content.

Opting out applies only to telemetry emitted by OpenShell. Third-party services, model providers, inference endpoints, agents, or tools that you configure and use with OpenShell may have their own terms and privacy practices.

We publish aggregate usage trends from this telemetry every two weeks. See the community telemetry reports for the latest summary.

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.