What can I help with?

Hanzo Chat runs on open models. Free to start — open hanzo.chat.

Run it on your own machine

Most AI platforms hand you an API key. We hand you the platform. One binary, and hanzo serve brings up the cloud itself — control plane, identity, secrets, gateway, storage, pub/sub — on your own hardware.

It is the same code we run in our own cloud, under an open licence. Point a client at localhost or at api.hanzo.ai — same API, nothing else changes.

curl -fsSL https://hanzo.sh | shInstall options

Desktop

The whole stack as an app. The agent node ships inside the bundle as a sidecar; inference comes from the engine, running locally or on your LAN.

View source

CLI

One static Rust binary — a coding agent, the MCP server, and every product of the cloud from your terminal. No runtime, no daemon.

View source

Engine

The inference engine that actually runs the model. LLM and embedding serving in Rust, built for local hardware first.

View source

ML

The compute core underneath: multi-backend tensors across CPU, CUDA, Metal, ROCm and Vulkan, with quantization built in.

View source

Introducing Enso · Hanzo Cloud

Enso, our frontier model

Hanzo’s flagship AI — one model that orchestrates the world’s best models into a single API to tackle complex, multi-step work. Available on Hanzo Cloud.

Explore Enso Try in Hanzo Chat

FlashProUltraone OpenAI- and Anthropic-compatible API