Skip to content

Interlaken Cloud

Type what you want. Get a URL.

A prompt becomes a live application. Underneath it: real machines, private networks, disks and databases.

Get started Explore the platform
  • Firecracker microVMs
  • VPC networking
  • Replicated storage
  • Managed PostgreSQL
  • Kubernetes
  • AI agents

01 From prompt to URL

One sentence in. One address out.

An animated illustration: a prompt is typed into Interlaken, which plans the app, provisions a PostgreSQL database, builds a container image, deploys it behind a load balancer, issues a TLS certificate and opens the finished page in a browser window at https://barbershop.interlaken.ai.

03 Capabilities

Everything a real application needs.

Seven areas, one account, one network, one bill.

  1. Git · App Builder · WordPress

    Deploy

    Describe an app or push a repository. Interlaken builds it and hands back a URL.

    Read more
  2. VMs · microVMs · containers

    Compute

    Virtual machines, Firecracker microVMs and containers on one fabric.

    Read more
  3. VPC · load balancers · egress

    Networking

    Private networks, load balancers, public addresses and routed egress.

    Read more
  4. LINSTOR · DRBD · MinIO

    Storage

    Replicated block volumes, snapshots, images and S3-compatible buckets.

    Read more
  5. Five engines · KubeBlocks

    Databases

    Managed PostgreSQL, MySQL, MongoDB, Redis and Elasticsearch.

    Read more
  6. k3s · CNI · CSI · kubeconfig

    Kubernetes

    Managed clusters on your own machines, with storage and load balancing wired in.

    Read more
  7. Claude · Codex · MCP

    AI agents

    Development agents with their own sandbox, terminal and repository access.

    Read more

04 Underneath

What your app actually runs on.

Every application gets a private network. Traffic arrives at a load balancer, crosses into your VPC, reaches your machines, and lands on disks replicated to more than one host.

Internet Load balancer L4 · TLS · HTTP/3 Your VPC 10.0.0.0/16 Subnet · web 10.0.1.0/24 Subnet · data 10.0.2.0/24 microVMs Containers Replicated disks mirrored writes
Simplified. The console draws the real one, with the addresses filled in.
ways to run code VMs, Firecracker microVMs, containers
0
managed database engines PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch
0
second to boot a microVM Firecracker, measured on our own hosts
0
account, one network, one bill usage-metered, every resource on it
0

Counts are what the platform ships; the microVM boot figure is approximate, measured on our own hosts.

VPC peering Snapshots Golden images S3-compatible buckets PostgreSQL MySQL MongoDB Redis Elasticsearch Managed Kubernetes Firecracker microVMs Containers Autoscaling groups TLS termination HTTP/3 Public IPv4 and IPv6 SSH keys Certificates DNS records OAuth 2.1 MCP server Role-based access Metered billing

05 AI agents

Engineers that live in your cloud.

An agent gets a real sandbox in your own tenant — a machine with a filesystem, a terminal and the repositories you hand it. Give it a role, put it in a team, connect Claude or Codex.

01 / 04

Workspace

A workspace binds a repository to a chat. You say what you want; the agent asks what it still needs to know, then starts working.

02 / 04

Terminal

Every run is its own microVM with its own kernel and disk. The agent runs commands, fixes what breaks and never shares a sandbox.

03 / 04

Repository

The code stays in your repository the whole time. Every step the agent takes is written into the chat, so nothing happens out of sight.

04 / 04

Push

The agent commits and pushes the branch. The push triggers a build on your deploy server, and the app updates on its own URL.

Start

Ship something today.

Create an account, type one sentence, and see what comes back. Billing is usage-based — you pay for what you run.