microsrv
stable VMs on interruptible cloud capacity
Major cloud providers sell spare capacity at steep discounts, but can reclaim it at any time. microsrv makes that capacity behave like stable VMs by live-migrating memory and running processes before a host is shut down. Applications keep running without restarts, while disks, IP addresses, and active connections remain intact.
Traffic flowing
HTTPS and the private connection are active
> how it works
VMs run on interruptible capacity from major cloud providers at about 40% below standard rates. You create, connect, and operate them as usual while the orchestrator manages host changes and preserves disks and network identity.
01
Live migration transfers memory and running processes to a new host. Your workload keeps running without restarting or losing its in-memory cache, while network connections and addresses remain unchanged.
The orchestrator tracks spare vCPU and memory on adjacent servers to keep capacity available when a VM needs to move.
Paid vCPUs belong exclusively to your VM and are not shared with other customers.
A provider notice triggers live RAM migration. Running processes continue executing on the new host without restarting the application.
When there is no time for live migration, the VM automatically launches from a replicated copy.
PVM · kernel
Guest VMs run on interruptible cloud instances without hardware nested virtualization. The PVM (pagetable-based VM) kernel removes dependence on nested KVM, which providers often disable.
Read more on LWN →02
Providers offer spare capacity at up to 70% off, but warn that hosts can be reclaimed whenever demand spikes.
Without automated orchestration, this capacity is typically used for non-critical or interruption-tolerant workloads. Our platform handles the operational burden: it monitors provider notices, reserves capacity on adjacent servers, and moves or recovers VMs when a host is reclaimed.
In the examples below, total cost is about 40% less than the same provider’s standard rate.
interruptible capacity + microsrv orchestration = stable VM at a lower price
See the price comparison →03
Create a VM, connect over SSH, and deploy your services. Host migration happens automatically in the background.
Pick CPU, memory, and disks. Configure initial setup on boot via cloud-init.
Get a persistent private IP and replicated disks that remain intact across migrations.
Connect via secure SSH or use the built-in gateway with custom domain names and TLS.
Run web apps, databases, or background jobs. When a host is reclaimed, the platform migrates the VM or recovers it automatically.
04
Public services, internal systems, and background workers run just like on traditional VMs.
Web apps, databases, AI agents, and background workers get dedicated vCPUs, a private network, and a stable SSH address.
> pricing
VMs run on interruptible capacity while the platform provides 99.9% availability. The table below shows the cost of a typical three-node cluster.
Reference workload
3 × (4 dedicated vCPUs · 8 GB RAM · 40 GB SSD) — small cluster / Kubernetes node group
How pricing is calculated
Self-hosted microsrv
Deploy microsrv on your own servers or in your cloud, and manage VMs, networking, and migrations from one place.
Estimated monthly totals for 3 × (4 vCPU · 8 GB · 40 GB SSD). Cloud A and Cloud B are standard rates from public provider calculators. Final microsrv pricing depends on the region, available capacity, and hosting terms.
> developer & ops features
Network isolation, secure access, and service publishing work out of the box—without additional infrastructure to configure.
Connect via ssh -A <vm>@microsrv.ru. Port 22 is never exposed to the internet, and no public IP is needed.
Inject SSH keys, initialization scripts, and configurations during first-boot VM setup.
Isolated private networks with stable internal IPs and in-kernel protection against IP/MAC spoofing.
Reach external APIs, Git repos, and registries while keeping the VM hidden from public ingress.
Expose HTTPS apps and TCP databases with permanent <vm>.microsrv.ru hostnames and automated TLS.
Live RAM migration ensures your application keeps running without restarts, while eBPF identity rebinding keeps open TCP connections intact.
No public IP on the VM. No VM SSH port exposed to the internet. Same address regardless of the current physical host.
$ ssh -A <vm>@microsrv.rumicrosrv: connection to <vm> establishedWelcome to Ubuntu 24.04.2 LTS (GNU/Linux 6.8.0-60-generic x86_64) * Documentation: https://help.ubuntu.com * Management: https://landscape.canonical.com System information: 4 vCPU · 8 GB RAM · 40 GB SSDPrivate address: 10.42.0.17 Last login: Fri Jul 24 20:51:08 2026 from 10.42.0.1ubuntu@<vm>:~$The included microsrv gateway exposes supported workloads over hostname-based HTTPS and TLS/SNI-routed TCP, without requiring a public IP for the VM.
$ curl -v https://<vm>.microsrv.ru* Host <vm>.microsrv.ru:443 was resolved* Connected to <vm>.microsrv.ru port 443* SSL connection using TLSv1.3 / TLS_AES_256_GCM_SHA384> GET / HTTP/2> Host: <vm>.microsrv.ru< HTTP/2 200< server: microsrv-gateway< content-type: application/json {"hello":"from <vm>"}$$ psql "host=<vm>.microsrv.ru sslmode=require"psql (16.3, server 16.3)SSL connection (protocol: TLSv1.3, cipher: TLS_AES_256_GCM_SHA384)Type "help" for help. <vm>=> SELECT current_database(), inet_server_addr(); current_database | inet_server_addr------------------+------------------ app | 10.42.0.17(1 row) <vm>=>> roadmap
Explicit future capabilities — not current product.
> blog
Short notes on interruptible capacity, networking, and how microsrv keeps VMs running through host interruptions.
A deep dive into microsrv's network layer: decoupling guest network identity from physical hosts, isolated VPCs, unified SSH and HTTPS/SNI API gateways, and seamless TCP session persistence during live migration.
A comprehensive guide to Spot and Preemptible instances: how providers offer up to 80% discounts, how eviction notices work, what the limitations are, and how to design applications for them.