linkgo
OpenShell

OpenShell

AI

OpenShell is NVIDIA's open-source runtime that sandboxes autonomous AI agents with kernel-level policy enforcement and verified policy changes.

-(0 Reviews)
Free Available
Starting from Free
Visit Official Site

About OpenShell

OpenShell is an open-source runtime from NVIDIA for running fleets of autonomous AI agents safely and privately. Each agent runs in an isolated sandbox where kernel controls confine file access and system calls, and every network connection passes through a policy check before leaving the sandbox. Teams declare in a policy what each agent may touch, and OpenShell enforces it at runtime. Credentials are never exposed to agents and are injected only into requests bound for approved endpoints. Policy changes are checked with formal verification so risky new access, such as reaching a new host with credentials, waits for human review. It runs on Linux, macOS on Apple Silicon and experimentally Windows with WSL 2 using Docker, Podman or host virtualization, and is Apache 2.0 licensed.

Key Features

Kernel-Level Enforcement: Confines which files an agent can access and which system calls it can make, enforced at runtime.
Network Policy Checks: Every outbound connection from the sandbox passes through a policy check before it leaves.
Credential Isolation: Agents never see real credentials; OpenShell adds them only to requests for approved endpoints.
Formally Verified Policy Changes: Uses formal verification to flag risky new access before a policy change is approved for human review.
Declarative Policies: Define filesystem, network and process rules per agent in a policy file.
Gateways and Providers: A control plane for sandboxes, policy and access, plus providers for credentials and inference.
Sandbox Images and GPUs: Supports configurable sandbox images, runtimes and GPU access with a minimal Ubuntu default image.
Cross-Platform Install: Installer sets up the CLI and a local gateway on Linux and Apple Silicon macOS using Docker, Podman or virtualization.

Use Cases

Safe Agent Execution: Let coding agents install packages and call APIs without unrestricted access to your data.
Secrets Protection: Keep API keys out of agent reach while still allowing calls to approved endpoints.
Agent Fleet Governance: Apply consistent policies across many autonomous agents in a team.
Policy Review Workflows: Require human approval for policy changes that grant risky new access.
Local Agent Experimentation: Try agents such as OpenCode in an isolated sandbox against free models.
Enterprise Compliance: Provide auditable, enforced boundaries for agents operating on sensitive systems.

Frequently asked questions about OpenShell

What is OpenShell?

OpenShell is NVIDIA's open-source runtime that sandboxes autonomous AI agents with kernel-level policy enforcement and verified policy changes.

How does OpenShell work?

OpenShell works by combining Kernel-Level Enforcement: Confines which files an agent can access and which system calls it can make, enforced at runtime., Network Policy Checks: Every outbound connection from the sandbox passes through a policy check before it leaves., Credential Isolation: Agents never see real credentials; OpenShell adds them only to requests for approved endpoints., Formally Verified Policy Changes: Uses formal verification to flag risky new access before a policy change is approved for human review., Declarative Policies: Define filesystem, network and process rules per agent in a policy file. to help users with Safe Agent Execution: Let coding agents install packages and call APIs without unrestricted access to your data., Secrets Protection: Keep API keys out of agent reach while still allowing calls to approved endpoints., Agent Fleet Governance: Apply consistent policies across many autonomous agents in a team., Policy Review Workflows: Require human approval for policy changes that grant risky new access., Local Agent Experimentation: Try agents such as OpenCode in an isolated sandbox against free models..

What are the main features of OpenShell?

Key features include Kernel-Level Enforcement: Confines which files an agent can access and which system calls it can make, enforced at runtime., Network Policy Checks: Every outbound connection from the sandbox passes through a policy check before it leaves., Credential Isolation: Agents never see real credentials; OpenShell adds them only to requests for approved endpoints., Formally Verified Policy Changes: Uses formal verification to flag risky new access before a policy change is approved for human review., Declarative Policies: Define filesystem, network and process rules per agent in a policy file..

Who is OpenShell for?

OpenShell is useful for anyone interested in Safe Agent Execution: Let coding agents install packages and call APIs without unrestricted access to your data., Secrets Protection: Keep API keys out of agent reach while still allowing calls to approved endpoints., Agent Fleet Governance: Apply consistent policies across many autonomous agents in a team., Policy Review Workflows: Require human approval for policy changes that grant risky new access., Local Agent Experimentation: Try agents such as OpenCode in an isolated sandbox against free models..

How much does OpenShell cost?

OpenShell is free to use.

How do I get started with OpenShell?

Visit https://github.com/NVIDIA/OpenShell to sign up and explore OpenShell.

Explore more AI Ai Services tools

Browse all Ai Services tools →

Compare OpenShell: vs BAND for Developers · vs NitroStack · vs GBrain · vs MentionBird

OpenShell - AI Tool Review | LinkGo