AI product Open source · Apache-2.0

OpenShell

OpenShell is an open-source runtime from NVIDIA and a structural safety safeguard for running fleets of autonomous AI agents in isolated sandboxes, complementing model-based policy checks. It lets agents read files, install packages, call APIs, and use credentials while enforcing declared filesystem, process, and network policies.

View repository Visit site Mentioned in 3 videos ↓

Overview

Each agent runs in a sandbox where kernel-level controls govern file access, system calls, and network connections. OpenShell also uses formal verification to review policy changes before approval, flagging newly permitted access such as connections to additional hosts with credentials or calls to new API methods. Credentials are withheld from agents and added only to requests bound for approved endpoints. The project provides a CLI, local gateway, sandbox lifecycle management, policy tooling, inference-provider routing, Kubernetes deployment, extensibility APIs, and Python, TypeScript, Go, and Rust SDKs.

What OpenShell is used for

3 uses taken from transcripts — each links to the moment in the video.

  • A secure, policy-governed runtime for autonomous AI agents. It runs agents in kernel-level sandboxes and enforces declarative policies governing access, credentials, and endpoints.

  • A structural open-agent-safety safeguard mentioned as complementary to model-based policy checks.

  • NVIDIA's open-source secure-by-design runtime for autonomous AI agents, running agents unmodified inside kernel-level sandboxes governed by declarative YAML policy, injecting credentials only into approved requests.

Videos mentioning OpenShell

3 in the library.