NVIDIA OpenShell
Sandboxed runtime for autonomous agents with declarative YAML policies on file, network and credential access.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, coding in the terminal, running code safely
Use cases
About NVIDIA OpenShell
NVIDIA OpenShell is listed in our sandboxes & code execution category and is aimed at builders. Sandboxed runtime for autonomous agents with declarative YAML policies on file, network and credential access. Pricing, as the maker states it: Open source (Apache 2.0). Maturity: Active; part of newly announced Open Agent Safety Platform. We last checked the official link on 2026-10-14.
What is NVIDIA OpenShell?
NVIDIA OpenShell is a safe, private runtime for fleets of autonomous AI agents. It lets agents read files, install packages, call APIs and use credentials without unrestricted access to your data, secrets or network.
Policies are declared in YAML for file, network and credential access. Version 0.1.x brought a stable release cadence, new isolation primitives and new APIs. It is Apache 2.0 licensed.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: docs.nvidia.com/openshell/latest.
Who is NVIDIA OpenShell for?
Teams running autonomous agents who need strict, declarative control over what they can touch.
NVIDIA OpenShell at a glance
- Open source: Yes (Apache License 2.0)
- GitHub: nvidia/openShell · 16,900 stars (as of Oct 21, 2026)
Key features
- Sandboxed runtime for agent fleets
- YAML policies for files, network and credentials
- Isolation primitives
- Apache 2.0
NVIDIA OpenShell FAQ
What is NVIDIA OpenShell?
NVIDIA OpenShell is a safe, private runtime for fleets of autonomous AI agents. It lets agents read files, install packages, call APIs and use credentials without unrestricted access to your data, secrets or network.
Who is NVIDIA OpenShell for?
Teams running autonomous agents who need strict, declarative control over what they can touch.
Is NVIDIA OpenShell free?
NVIDIA OpenShell's pricing, as the maker states it: Open source (Apache 2.0). Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is NVIDIA OpenShell open source?
Yes. NVIDIA OpenShell is released under the Apache License 2.0, according to its GitHub repository.
What are alternatives to NVIDIA OpenShell?
Similar tools include OpenSandbox, microsandbox, Perplexity SPACE, Sandbox0, nono and Judge0.
NVIDIA OpenShell ratings and reviews
Be the first to rate NVIDIA OpenShell: tap 1 to 5 stars below. A written review is optional.
NVIDIA OpenShell alternatives
Other sandboxes & code execution tools in our directory. See all sandboxes & code execution tools →
OpenSandbox
Secure, fast sandbox runtime for AI agents to run code.
microsandbox
Local-first microVM runtime for running untrusted agent code safely.
Perplexity SPACE
Perplexity's open-source sandbox platform that runs each agent task in its own Firecracker microVM, with credentials and network access controlled from outside.
Sandbox0
Sandbox0 is a managed sandbox runtime that gives each AI agent an isolated cloud computer where it can run code, install software, manage files and control network access. The whole writable root filesystem persists across incremental checkpoints and grows automatically as it fills, so an agent can pause compute between tasks and resume the same sandbox later with its tools, dependencies and files intact. It adds snapshots and restore, SSH, egress proxy and credential injection, private previews, Docker in the sandbox, webhooks, warm pools and custom templates, with integrations for LangChain Deep Agents, OpenAI Agents, Vercel and GitHub CI. Sandboxes run under gVisor isolation with Nomad scheduling.
nono
Zero-trust sandboxing for agent runtimes.
Judge0
Sandboxed code execution system for running untrusted code from people and AI.
Popular searches with this tool
🧭 Task guides: Sandboxes and secure execution tools for coding agents
Badge for makers
Built NVIDIA OpenShell? Add this badge to your README or site. It links back to this page. About badges
