INFRASTRUCTURE • CURATED • UPDATED SEP 29, 2026

NVIDIA OpenShell

Open-source sandbox runtime that fences in what AI agents can touch
Price
Free
API
No
Weights
Yes

OpenShell is NVIDIA's open-source runtime for running AI agents inside a sandbox. It sits beneath the agent harness, runs the agent without privileges, limits which files it can reach, filters system calls at the kernel level, and checks every network request against policy by binary, destination, method and path. Nothing is allowed by default, credentials are only supplied where policy permits, a policy-aware router controls which model endpoints the agent can call, and every decision is logged. It supports Claude Code, Codex, GitHub Copilot CLI, Hermes, LangChain Deep Agents, OpenClaw and OpenCode, and runs on Docker, Podman, Kubernetes via Helm, and NVIDIA DGX Spark and DGX Station. First announced in March 2026, it became the software half of NVIDIA's Open Agent Safety Platform on September 28, 2026, alongside Sentry, a monitor that runs on BlueField-4 hardware.

After a run of agents escaping their test environments, the useful question is where the fence lives. OpenShell enforces policy outside the agent's own process, where a prompt cannot talk it out of the rules, and it works with the coding agents people already use. It is free, open source under Apache 2.0, and needs no special hardware.

Pricing Free
Platforms local
API No
Open Source Yes
Modalities Infrastructure
Best For Best Open-Source Agent Sandbox
Date Added 2026-09-29
  • ✓Deny-by-default policy for files, network, processes and credentials
  • ✓Enforcement runs outside the agent, so it cannot be prompted away
  • ✓Works with Claude Code, Codex, Copilot CLI, OpenClaw and other harnesses
  • ✓Apache 2.0 open source, runs on Docker, Podman or Kubernetes
  • ✓Every allow and deny decision is auditable
  • ⚠Policies take real work to write well; too loose and the sandbox protects little
  • ⚠Sentry, the hardware monitor in NVIDIA's full platform, needs BlueField-4 hardware most teams do not have
  • ⚠Does not judge whether an allowed action is a good idea, only whether policy permits it

Clone github.com/NVIDIA/OpenShell and follow the docs to run your agent in a sandbox under Docker or Podman. Start from a tight policy and open access only as the agent needs it; the GitHub push tutorial in the docs is a good first example.

Free Completely free
View NVIDIA OpenShell Alternatives (2026) →

Compare NVIDIA OpenShell with 5+ similar infrastructure AI tools.

❓
Q

Is NVIDIA OpenShell free?

A

Yes, NVIDIA OpenShell is completely free to use.

Q

Does NVIDIA OpenShell have an API?

A

No, NVIDIA OpenShell does not appear to offer a public API.

Q

What is NVIDIA OpenShell best for?

A

NVIDIA OpenShell is best for Best Open-Source Agent Sandbox. OpenShell is NVIDIA's open-source runtime for running AI agents inside a sandbox. After a run of agents escaping their test environments, the useful question is where the fence lives. OpenShell enforces policy outside the agent's own process, where a prompt cannot talk it out of the rules, and it works with the coding agents people already use. It is free, open source under Apache 2.0, and needs no special hardware.

Q

What platforms does NVIDIA OpenShell support?

A

NVIDIA OpenShell supports local.

Q

Is NVIDIA OpenShell open source?

A

Yes, NVIDIA OpenShell is open source. You can access the source code on GitHub at https://github.com/NVIDIA/OpenShell.

Q

How do I get started with NVIDIA OpenShell?

A

Clone github.com/NVIDIA/OpenShell and follow the docs to run your agent in a sandbox under Docker or Podman. Start from a tight policy and open access only as the agent needs it; the GitHub push tutorial in the docs is a good first example.

🏷️

Work on NVIDIA OpenShell? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.

Featured on CuratedAI