Hanzo · Open AI Cloud
Build what’s next.
Start on your machine. Keep going in the cloud. Pick it up anywhere.
Open source · Local first · /v1 everywhere
Add rate limiting to the payments API.
Read 14 files. The limiter belongs in the gateway, not the handler — one place, every route.
Wrote gateway/limit.go and a test at 100 req/min per key. Tests pass.
Same work. Every surface.
One session, one history, one set of permissions. Move between the app, a terminal, the cloud and your editor and pick up mid-sentence.
Meet Enso
Ask once.
Describe what you want. Enso reads the request, picks the models, calls the tools and stands up the infrastructure — then hands you back the work, wherever you are.
Start typing. The system draws itself behind you.
ON YOUR OWN MACHINE
Your laptop is the cluster.
One line installs the CLI. The next one boots a real Kubernetes control plane inside a native microVM — Virtualization.framework on a Mac, KVM on Linux — and hands you a kubeconfig your existing tools already understand. Nothing to install underneath it.
to boot the microVM — the same on Apple silicon, Ryzen and GB10.
from cold to a Ready node, every platform we ship.
and no daemon, no VM manager, and no cloud account to open.
START
Say what you want.
A sentence is enough to open a chat, start a coding agent, or put something in the cloud.