hanzoai/chat
2
0
Fork 0
mirror of https://github.com/hanzoai/chat.git synced 2026-09-30 20:51:17 +00:00
Code Issues Releases Activity
Files
mirror/work
chat/docs/platform-overview.md
T
zeekayandHanzo Dev 5960df513a Delete the LiteLLM proxy this repo has not been for a long time 
266 files of upstream residue, none of it reachable from anything that builds
or runs. chat is a Node application that reaches models through api.hanzo.ai;
what came out is a Python proxy's build system, test suite and CI:

  docker/    every image in it CMDs `litellm`, one is FROM ghcr.io/berriai/litellm
             — the upstream vendor's own image — and Dockerfile.dev is
             python:3.11-slim + pip install litellm[proxy]
  tests/     231 files, 181 of them .py, including an enterprise/ tree; wired to
             no suite in this repo
  ci_cd/     Prisma migration scripts for schema.prisma, which declares
             LiteLLM_BudgetTable and friends while no package.json anywhere
             depends on prisma
  deploy/    the migrations those scripts generate
  config.yaml, the proxy's model_list; compose.dev.yml, whose `command: npm run
  dev` was aimed at that Python image and could never have run; docker-compose.yml,
  a near-identical twin of compose.yml; .pre-commit-config.yaml, whose hooks
  filter on litellm/, litellm_proxy_extras/ and enterprise/.

The Makefile is the part that was actively wrong rather than merely dead:
`build-prod` ran `docker build -f docker/Dockerfile -t hanzoai/chat:latest`,
which builds the LiteLLM image and tags it as chat. `dev` and `dev-full` drove
compose.dev.yml and a with-router profile pointing at hanzoai/llm:latest. dev
now runs the two watch commands this repo actually has, build-prod builds
Dockerfile.multi — the image deploy.yml ships — and dev-full and logs-router are
gone with the router they logged.

Verified before cutting: nothing under Dockerfile.multi, Dockerfile.static,
compose.yml, hanzo.yml, package.json or .hanzo/workflows/ reaches any deleted
path. The `docker/` hits in deploy.yml are docker/setup-buildx-action, an action
namespace. `.do/gitnexus` copies its own entrypoint.sh, not the one in docker/.

Co-authored-by: Hanzo Dev <[email protected]>
2026-08-20 21:04:06 -07:00

5.4 KiB
Raw Permalink Blame History

🚀 Hanzo AI Platform - Complete Stack

Welcome to the Hanzo AI Platform! This is a production-ready, open-source AI infrastructure stack that you can run locally or deploy to production.

🎯 Quick Start

# Clone and start the complete platform
git clone https://github.com/hanzoai/chat.git
cd chat
docker compose up -d

# Wait for services to be healthy (about 1-2 minutes)
docker compose ps

# Access the platform
open http://localhost:3000  # Cloud Dashboard
open http://localhost:3081  # Chat Interface
open http://localhost:8000  # IAM Dashboard

🏗️ What's Included

Core Services

Service Port Description Production URL
Cloud 3000 AI Platform Dashboard cloud.hanzo.ai
Chat 3081 AI Chat Interface hanzo.chat
Router 4000 LLM Gateway (100+ providers) api.hanzo.ai
IAM 8000 Identity & Access Management hanzo.id
Services 3333 Service Orchestration hanzo.services

Infrastructure

  • PostgreSQL - Primary database
  • MySQL - IAM database
  • MongoDB - Chat storage
  • Hanzo Datastore - Analytics
  • Redis - Caching
  • Meilisearch - Full-text search
  • MinIO - S3-compatible storage

🔑 Default Access

Admin Account

Service Keys

  • Router API: sk-hanzo-master-key
  • MinIO: minio / miniosecret

🎨 Key Features

For Developers

  • Local Dev Mode - No org/team setup required
  • Full Visibility - Access all logs and metrics
  • Hot Reload - Development mode with live updates
  • Production Parity - Same stack as production

Platform Capabilities

  • Multi-Model AI - Route between 100+ LLM providers
  • Cost Tracking - Monitor and control AI spending
  • Usage Analytics - Full metrics and monitoring
  • Team Management - Multi-tenant support (production)
  • Social Login - Google, GitHub, and more
  • API Gateway - OpenAI-compatible endpoints

📊 Using the Platform

1. Configure AI Models (Cloud Dashboard)

  1. Navigate to http://localhost:3000
  2. Login with [email protected]
  3. Go to Models section
  4. Add your API keys:
    • OpenAI
    • Anthropic
    • Custom providers
  5. Set pricing and rate limits

2. Chat with AI

  1. Open http://localhost:3081
  2. Login via IAM (redirects automatically)
  3. Select configured models
  4. Start chatting!

3. Monitor Usage

  • View metrics in Cloud dashboard
  • Check logs in real-time
  • Track costs per model/user
  • Analyze conversation patterns

🛠️ Configuration

Essential Environment Variables

Create .env file:

# Required: At least one LLM provider
OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...

# Optional: Social login
GOOGLE_CLIENT_ID=...
GOOGLE_CLIENT_SECRET=...
GITHUB_CLIENT_ID=...
GITHUB_CLIENT_SECRET=...

# Optional: Production domains
PRODUCTION_IAM_URL=https://hanzo.id
PRODUCTION_CLOUD_URL=https://cloud.hanzo.ai
PRODUCTION_API_URL=https://api.hanzo.ai

🔄 Development Workflow

Hot Reload Development

# API and client, both in watch mode
npm run backend:dev & npm run frontend:dev

# Services with hot reload:
# - Cloud (Next.js)
# - Chat (React)
# - Router (Python)
# - Services (NestJS)

Adding New Models

  1. Configure in Cloud dashboard
  2. Router automatically picks up changes
  3. Models available in Chat immediately

Customizing Auth

  1. Edit IAM configuration
  2. Add OAuth providers
  3. Configure redirects
  4. Update Chat SSO settings

🚢 Production Deployment

Domain Setup

Service Development Production
IAM localhost:8000 hanzo.id
Cloud localhost:3000 cloud.hanzo.ai
API localhost:4000 api.hanzo.ai
Chat localhost:3081 hanzo.chat
Services localhost:3333 hanzo.services

Migration Checklist

  • Update domain configurations
  • Configure SSL certificates
  • Set production environment variables
  • Enable organization mode
  • Configure backup strategies
  • Set up monitoring/alerting
  • Configure rate limiting
  • Enable audit logging

📚 Documentation

🤝 Community & Support

🎯 Use Cases

For Startups

  • Complete AI infrastructure from day one
  • Scale from local to global deployment
  • Pay only for what you use

For Enterprises

  • Self-hosted AI platform
  • Full data sovereignty
  • Custom model integration
  • Compliance-ready logging

For Developers

  • Learn from production architecture
  • Contribute improvements
  • Build on top of the platform
  • Create custom integrations

🔮 Roadmap

  • Kubernetes Helm charts
  • One-click cloud deployment
  • Mobile SDKs
  • More LLM providers
  • Enhanced monitoring dashboard
  • Automated model selection
  • Cost optimization algorithms

📝 License

MIT License - Use freely in your projects!

Ready to build the future of AI? Start with docker compose up -d and you're running the same stack that powers Hanzo AI in production! 🚀

Reference in New Issue View Git Blame Copy Permalink