AI BriefingNVIDIA Donates OpenShell to CNCF and Launches Kubernetes Tools for AI Factories
·2026.11.11 01:00
Key point
NVIDIA contributes OpenShell and Agent Substrate to the CNCF Sandbox and releases NVIDIA Snapshot, which reduces vLLM startup times from minutes to seconds.
Details
- NVIDIA contributes OpenShell, a runtime for securing autonomous agents, to the Cloud Native Computing Foundation (CNCF) Sandbox and supports Google-led Agent Substrate for scaling agent workloads on Kubernetes.
- NVIDIA Snapshot restores checkpointed inference replicas in seconds without model reload, reducing vLLM startup times from 2 to 8.5 minutes to 6 to 34 seconds in benchmarks by Saturn Cloud.
- NVIDIA Kubernetes Engine (NVKE) and NVIDIA Kubernetes Recipes (NVKR) enter public preview to automate cluster lifecycle management and provide signed, version-pinned images for managed Kubernetes services on GPU infrastructure.
- OpenShell has received tens of thousands of contributions in less than a year, with hundreds of organizations using it to apply deterministic controls and governance to agent activity.
- Crusoe tested GLM-5.3 on Crusoe Cloud using NVIDIA HGX B300 systems, reducing workload readiness time from roughly eight minutes to 31 seconds.
- Ecosystem partners including Mirantis, Netris, OpenNebula Systems, Rafay, Spectro Cloud, vCluster, Firmus, and SK Telecom are aligning with NVIDIA to integrate NVKE and NVKR capabilities.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Nvidia Used Circular Financing to Keep GPU Prices High, WSJ Report ClaimsResearch finds 24,664 Lovable apps exposing sensitive data without login