Hanzo Chat

The chat app on Hanzo Cloud — enso and Zen models, MCP tools, agents, file uploads and RAG. Hosted at chat.hanzo.ai, or self-host it.

Hanzo Chat is the chat app on Hanzo Cloud, built on LibreChat. It runs our own models — the enso frontier family and the Zen open-weight family — with MCP tools, configurable agents, file uploads with RAG, vision, conversation history, presets and plugins. Models from outside labs are carried too, and appear in the same model menu.

Available as a hosted service at chat.hanzo.ai or self-hosted via Docker.

Quick Start

Hosted (Recommended)

Go to chat.hanzo.ai
Sign in with your Hanzo account
Your $5 free credit is applied automatically
Select a model and start chatting

Self-Hosted

git clone https://github.com/hanzoai/chat
cd chat
cp .env.example .env
# Edit .env with your HANZO_API_KEY
docker compose up -d
# Open http://localhost:3081

The call

curl

CLI

TypeScript

Python

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen6",
    "messages": [{"role": "user", "content": "Hello, Zen."}]
  }'

hanzo chat completions \
  --model zen6 \
  --messages '[{"role":"user","content":"Hello, Zen."}]'

import { Hanzo } from '@hanzo/ai'

const hanzo = new Hanzo({ secretKey: process.env.HANZO_API_KEY })

const completion = await hanzo.chat.completions.create({
  model: 'zen6',
  messages: [{ role: 'user', content: 'Hello, Zen.' }],
})
console.log(completion.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["HANZO_API_KEY"],
    base_url="https://api.hanzo.ai/v1",
)

response = client.chat.completions.create(
    model="zen6",
    messages=[{"role": "user", "content": "Hello, Zen."}]
)
print(response.choices[0].message.content)

/v1/chat/completions takes and returns the chat-completions JSON shape, which is why the Python tab is the openai client with its base URL moved: any client already written against that shape works here unchanged. Model ids are not portable across vendors, though — zen6 and enso exist only here. The SDKs covers what each language ships and when to reach past the chat route into the rest of /v1.

Architecture

┌─────────────────────────────────────────────────────────────┐
│                        HANZO CHAT                           │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────────┐  │
│  │ React Client │  │ Node.js API  │  │    DocumentDB    │  │
│  │              │  │              │  │                  │  │
│  │ - Chat UI    │  │ - REST API   │  │ - Messages       │  │
│  │ - Model Sel  │  │ - WebSocket  │  │ - Conversations  │  │
│  │ - File Upload│  │ - MCP Broker │  │ - Users          │  │
│  │ - Agents     │  │ - Auth       │  │ - Presets        │  │
│  └──────────────┘  └──────────────┘  └──────────────────┘  │
│                                                             │
│  ┌─────────────────────────────────────────────────────┐    │
│  │              Provider Layer (AI API)            │    │
│  │  Zen · OpenAI · Anthropic · Google · Meta · …       │    │
│  └─────────────────────────────────────────────────────┘    │
│                                                             │
│  ┌─────────────────────────────────────────────────────┐    │
│  │  Search       │  KV     │  S3     │  RAG API       │    │
│  └─────────────────────────────────────────────────────┘    │
│                                                             │
└─────────────────────────────────────────────────────────────┘