Radar / AI security / NVIDIA OpenShell joins CNCF
NVIDIA OpenShell joins CNCF: open governance for securing autonomous agents
NVIDIA contributed OpenShell, its open-source runtime for securing and governing autonomous agents, to the CNCF as a Sandbox project.
Why it matters
Puts agent guardrails in neutral, community-led hands: deterministic, kernel-isolated sandboxes with declarative policies, instead of each team bolting its own sandbox onto agents.
What you could build with it
A platform team running coding agents in production could deploy OpenShell as the policy layer under its agents, so filesystem, network and credential access are enforced outside the agent process and cannot be talked away by a prompt injection.
Does it hold up?
Already in real use — NVIDIA says hundreds of organisations run it, and it supports Claude Code, Codex, Copilot CLI, OpenCode and other harnesses. The CNCF governance move is still underway, so expect repo and org churn in the short term.
Built with NVIDIA OpenShell joins CNCF
- NVIDIA Donates OpenShell to CNCF and Adds Open-Source AI Factory ToolsUnite.AI · Notes the runtime is Apache 2.0, that code stays at NVIDIA/OpenShell while development moves to the ai-openshell org, and the companion Agent Substrate contribution.
- Nvidia donates OpenShell agent-security runtime to the CNCF and adds Kubernetes tools for AI factoriesMLQ · Covers the KubeCon announcement, the hundreds of organisations NVIDIA says already use OpenShell, and the NVKE/NVKR public previews.
- NVIDIA expands open-source contributions for AI agentsVARINDIA · Reports OpenShell's deterministic controls on agent tool use, inference access and workloads, plus the OpenShell-Agent Substrate integration.
- NVIDIA/OpenShellgithub · 21,479 ★ · The OpenShell runtime itself: kernel-isolated agent sandboxes with Cedar-based declarative YAML policies, currently migrating to the ai-openshell org.
Learn more
First spotted on article: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.