NVIDIA OpenShell: Isolated Runtime for Autonomous AI Agents

RepositoryNVIDIA/OpenShellTool

NVIDIA OpenShell is an open-source runtime written in Rust designed to run autonomous AI agents in secure sandboxes. It enforces declarative policies at the kernel level and guards access to network routes and credentials.

Key points

  1. Kernel-level enforcement: OpenShell confines file operations, system calls, and network traffic for each agent sandbox via kernel controls.
  2. Credential isolation: Agents never inspect raw secrets; OpenShell injects credentials only into outbound calls targeted at authorized endpoints.
  3. Formal verification for policies: Proposed policy modifications are evaluated via formal verification to flag high-risk access rights for human approval.
  4. Platform compatibility: Runs on Linux, macOS (Apple Silicon), and experimentally on Windows via WSL 2, relying on Docker, Podman, or host virtualization.

Why it matters

As autonomous agents execute commands, install software, and call external APIs, unconstrained execution risks data exposure and system compromise. OpenShell allows teams to grant agent capabilities while strictly controlling access boundaries.

Analysis

OpenShell tackles the critical security challenges of autonomous agent execution. Built in Rust and structured around a gateway, supervisor, and sandbox model, it bridges agent independence with robust infrastructure control. While its 0.1.x version badge and experimental WSL 2 support reflect early-stage software, strong community traction and NVIDIA's backing establish it as an important tool for DevOps and security teams managing agent fleets.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 18 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:microsoft/mxc

    Microsoft eXecution Container (MXC): Sandboxed Execution for Untrusted Code

    Microsoft eXecution Container (MXC) is a cross-platform sandboxed code execution framework designed for running untrusted workloads such as AI model output, plugins, and tools across Windows, Linux, and macOS. It wraps native OS containment mechanisms and VMs into a unified policy engine and typed SDKs.

    1.8kstarsRust

    AI & LLMs· Tool

  • Repository:agent-substrate/substrate

    Agent Substrate: Zero-Trust Sandboxing for Autonomous Agents on Kubernetes

    Agent Substrate is an open-source Go runtime designed to run millions of agent workloads securely and efficiently on Kubernetes. It isolates untrusted code using microVMs or gVisor and snapshots idle agents to save resources.

    5.4kstarsGo

    AI & LLMs· Tool

  • Article:Beth Pariseau

    NanoClaw: Docker Sandboxes provide microVM isolation for AI agents

    Docker has partnered with NanoCo to run the NanoClaw AI agent within Docker Sandboxes. The integration relies on local microVMs in Docker Desktop to provide a strict isolation boundary between autonomous agents and the host operating system.

    AI & LLMs· News

  • Repository:anthropics/sandbox-runtime

    Anthropic Sandbox Runtime: Lightweight Process Isolation Without Containers

    Anthropic's Sandbox Runtime (srt) is an open-source tool designed to enforce OS-level filesystem and network restrictions on arbitrary processes. Developed as a safety component for Claude Code, it isolates AI agents, MCP servers, and shell commands without requiring containerisation.

    5.1kstarsTypeScript

    AI & LLMs· Tool

  • Repository:CopilotKit/OpenBot

    OpenBot: Open-Source Platform for Isolated and Governed AI Coworkers

    OpenBot by CopilotKit is a self-hosted platform providing AI agents as coworkers. Each agent operates within its own dedicated computer environment, featuring a real browser, scoped file access, and explicit tool permissions.

    4.3kstarsTypeScript

    AI & LLMs· Tool

  • Link:Docker

    Docker Introduces Sandboxes, AI Governance, and Hardened Images for AI Agents

    Docker has expanded its platform with dedicated security capabilities for autonomous AI agents. Introducing Docker Sandboxes using microVM isolation, a centralised AI Governance console, and SLSA Level 3 Hardened Images, the platform aims to provide safe execution and compliance from local laptops to production.

    AI & LLMs· Announcement

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.