vcluster

module
v0.32.0-alpha.2 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Feb 11, 2026 License: Apache-2.0

README ยถ

vCluster

Flexible Tenancy For Kubernetes and AI Infra

GitHub stars Slack LinkedIn X

Website โ€ข Quickstart โ€ข Documentation โ€ข Blog โ€ข Slack


What is vCluster?

vCluster creates fully functional virtual Kubernetes clusters that run inside namespaces of a host cluster. Each virtual cluster has its own API server, runs on shared or dedicated infrastructure, and gives you flexible tenancy optionsโ€”from simple namespaces to fully dedicated clusters.

40M+ virtual clusters deployed by companies like Adobe, CoreWeave, Atlan, and NVIDIA.

vCluster gif


๐Ÿš€ Quick Start

# Install vCluster CLI
brew install loft-sh/tap/vcluster

# Create a virtual cluster
vcluster create my-vcluster --namespace team-x

# Use kubectl as usual - you're now in your virtual cluster!
kubectl get namespaces

Prerequisites: A running Kubernetes cluster and kubectl configured.

๐Ÿ‘‰ Full Quickstart Guide

๐ŸŽฎ Try Without Installing

No Kubernetes cluster? Try vCluster instantly in your browser:

Try on Killercoda


๐Ÿ†• What's New

Version Feature Description
v0.30 vCluster VPN & Netris Integration Tailscale-powered overlay network and automated network isolation for hybrid infrastructures
v0.29 Standalone Mode Run vCluster without a host clusterโ€”directly on bare metal or VMs
v0.28 Auto Nodes Karpenter-powered dynamic autoscaling for private nodes
v0.27 Private Nodes External nodes with full CNI/CSI isolation
v0.26 Hybrid Scheduling & Namespace Syncing Multiple scheduler support for AI/ML workloads and fine-grained namespace synchronization

๐Ÿ‘‰ Full Changelog


๐ŸŽฏ Use Cases

Use Case Description Learn More
GPU Cloud Providers Launch managed K8s for GPUs. Give customers isolated, production-grade Kubernetes fast. View โ†’
Internal GPU Platform Maximize GPU utilization without sacrificing isolation. Self-service access for AI/ML teams. View โ†’
AI Factory Run AI on-prem where your data lives. Multi-tenant K8s for training, fine-tuning, inference. View โ†’
Bare Metal K8s Run Kubernetes on bare metal with zero VMs. Isolation without expensive overhead. View โ†’
Software Vendors Ship Kubernetes-native software. Each customer gets their own isolated virtual cluster. View โ†’
Cost Savings Cut Kubernetes costs by consolidating clusters. Sleep mode pauses inactive clusters. View โ†’

๐Ÿ—๏ธ Architectures

vCluster offers multiple deployment architectures. Each builds on the previous, offering progressively more isolation.

Architecture Comparison

Shared Nodes Dedicated Nodes Private Nodes Standalone
Host Cluster Required Required Required Not Required
Node Isolation โŒ โœ… โœ… โœ…
CNI/CSI Isolation โŒ โŒ โœ… โœ…
Best For Dev/test, cost Production Compliance, GPU Bare metal, edge

๐Ÿ‘‰ Full Architecture Guide

Minimal Configuration

๐Ÿ”น Shared Nodes โ€” Maximum density, minimum cost Virtual clusters share the host cluster's nodes. Workloads run as regular pods in a namespace.
Shared Nodes Architecture
sync:
  fromHost:
    nodes:
      enabled: false  # Uses pseudo nodes
๐Ÿ”น Dedicated Nodes โ€” Isolated compute on labeled node pools Virtual clusters get their own set of labeled host nodes. Workloads are isolated but still managed by the host.
Dedicated Nodes Architecture
sync:
  fromHost:
    nodes:
      enabled: true
      selector:
        labels:
          tenant: my-tenant
๐Ÿ”น Private Nodes v0.27+ โ€” Full CNI/CSI isolation External nodes join the virtual cluster directly with their own CNI, CSI, and networking stack. Complete workload isolation from the host cluster.
Private Nodes Architecture
privateNodes:
  enabled: true
controlPlane:
  service:
    spec:
      type: NodePort
๐Ÿ”น vCluster Standalone v0.29+ โ€” No host cluster required Run vCluster without any host cluster. Deploy the control plane directly on bare metal or VMs. The highest level of isolationโ€”vCluster becomes the cluster.
Standalone Architecture
controlPlane:
  standalone:
    enabled: true
    joinNode:
      enabled: true
privateNodes:
  enabled: true
โšก Auto Nodes v0.28+ โ€” Karpenter-powered dynamic autoscaling Automatically provision and deprovision private nodes based on workload demand. Works across public cloud, private cloud, hybrid, and bare metal environments.
Auto Nodes Architecture
autoNodes:
  enabled: true
  nodeProvider: <provider>
privateNodes:
  enabled: true

โœจ Key Features

Feature Description
๐ŸŽ›๏ธ Isolated Control Plane Each vCluster gets its own API server, controller manager, and data storeโ€”complete Kubernetes API isolation
๐Ÿ”— Shared Platform Stack Leverage the host cluster's CNI, CSI, ingress, and other infrastructureโ€”no duplicate platform components
๐Ÿ”’ Security & Multi-Tenancy Tenants get admin access inside their vCluster while having minimal permissions on the host cluster
๐Ÿ”„ Resource Syncing Bidirectional sync of any Kubernetes resource. Pods, services, secrets, configmaps, CRDs, and more
๐Ÿ’ค Sleep Mode Pause inactive virtual clusters to save resources. Instant wake when needed
๐Ÿ”Œ Integrations Native support for cert-manager, external-secrets, KubeVirt, Istio, and metrics-server
๐Ÿ“Š High Availability Multiple replicas with leader election. Embedded etcd or external databases (PostgreSQL, MySQL, RDS)

๐Ÿข Trusted By

Atlan
100 โ†’ 1 clusters
Aussie Broadband
99% faster provisioning
CoreWeave
GPU cloud at scale
Lintasarta
170+ virtual clusters in prod
Fortune 500 Insurance Company
70% reduction in Kubernetes cost
Scanmetrix
99% faster deployments
Deloitte
Enterprise K8s platform
Ada
10x Developer Productivity
Trade Connectors
50% reduction in K8s ops cost

Also used by: NVIDIA, ABBYY, Lintasarta, Precisely, Shipwire, Trade Connectors, and many more.

๐Ÿ‘‰ View All Case Studies


๐Ÿ“š Learn More

๐ŸŽค Conference Talks
Event Speaker Title Link
KubeCon NA 2025 (Keynote) Lukas Gentele Autoscaling GPU Clusters Anywhere โ€” Hyperscalers, Neoclouds & Baremetal Watch
Platform Engineering Day NA 2025 (Keynote) Saiyam Pathak AI-Ready Platforms: Scaling Teams Without Scaling Costs Watch
Rejekts NA 2025 Hrittik Roy, Saiyam Pathak Beyond the Default Scheduler: Navigating GPU MultiTenancy in AI Era Watch
KubeCon EU 2025 Paco Xu, Saiyam Pathak A Huge Cluster or Multi-Clusters? Identifying the Bottleneck Watch
HashiConf 2025 Scott McAllister GPU sharing done right: Secrets, security, and scaling with Vault and vCluster Watch
FOSDEM 2025 Hrittik Roy, Saiyam Pathak Accelerating CI Pipelines: Rapid Kubernetes Testing with vCluster Watch
KubeCon India 2024 (Keynote) Saiyam Pathak From Outage To Observability: Lessons From a Kubernetes Meltdown Watch
CNCF Book Club 2024 Marc Boorshtein Kubernetes - An Enterprise Guide (vCluster) Watch
KCD NYC 2024 Lukas Gentele Tenant Autonomy & Isolation In Multi-Tenant Kubernetes Clusters Watch
KubeCon EU 2023 Ilia Medvedev, Kostis Kapelonis How We Securely Scaled Multi-Tenancy with VCluster, Crossplane, and Argo CD Watch
KubeCon NA 2022 Joseph Sandoval, Dan Garfield How Adobe Planned For Scale With Argo CD, Cluster API, And VCluster Watch
KubeCon NA 2022 Whitney Lee, Mauricio Salatino What a RUSH! Let's Deploy Straight to Production! Watch
TGI Kubernetes 2022 TGI TGI Kubernetes 188: vCluster Watch
Mirantis Tech Talks 2022 Mirantis Multi-tenancy & Isolation using Virtual Clusters (vCluster) in K8s Watch
Solo Webinar 2022 Rich Burroughs, Fabian Keller Speed your Istio development environment with vCluster Watch
KubeCon NA 2021 Lukas Gentele Beyond Namespaces: Virtual Clusters are the Future of Multi-Tenancy Watch
๐ŸŽฌ Community Voice
Channel Speaker Title Link
TeKanAid 2024 TeKanAid Getting Started with vCluster: Build Your IDP with Backstage, Crossplane, and ArgoCD Watch
Rawkode 2021 David McKay, Lukas Gentele Hands on Introduction to vCluster Watch
Kubesimplify 2021 Saiyam Pathak, Lukas Gentele Let's Learn vCluster Watch
TechWorld with Nana 2021 Nana Build your Self-Service Kubernetes Platform with Virtual Clusters Watch
DevOps Toolkit 2021 Viktor Farcic How To Create Virtual Kubernetes Clusters Watch

๐Ÿ‘‰ YouTube Channel โ€ข Blog


๐Ÿค Contributing

We welcome contributions! Check out our Contributing Guide to get started.


Resource Link
๐Ÿ“– Documentation vcluster.com/docs
๐Ÿ’ฌ Slack Community slack.loft.sh
๐ŸŒ Website vcluster.com
๐Ÿฆ X (Twitter) @vcluster
๐Ÿ’ผ LinkedIn vCluster
๐Ÿ’ฌ Chat with Expert Start Chat

๐Ÿ“œ License

vCluster is licensed under the Apache 2.0 License.


ยฉ 2026 Loft Labs. All rights reserved.

Made with โค๏ธ by the vCluster community.

โญ Star us on GitHub โ€” it helps!

Directories ยถ

Path Synopsis
cmd
vcluster command
vclusterctl command
hack
assets/cmd command
compat-matrix command
load-testing command
schema command
pkg
cli
k3s
k8s
log
pro
util/websocketproxy
Package websocketproxy is a reverse proxy for WebSocket connections.
Package websocketproxy is a reverse proxy for WebSocket connections.
test

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL