ChatRoutes

Open-source conversation management platform with advanced branching capabilities and multi-provider AI integration.

ChatRoutes lets you manage AI conversations with features like conversation branching (explore multiple discussion paths from any message), parallel responses (compare answers from different AI models side-by-side), and a full REST API for building custom integrations.

Features

• Conversation Branching - Fork conversations at any message to explore alternative paths
• Parallel Responses - Get responses from multiple AI models simultaneously
• Multi-Provider AI - OpenAI (GPT-4o, GPT-5), Anthropic (Claude), Google (Gemini), DeepSeek
• REST API - Complete API for programmatic access
• Guest Mode - Try without creating an account
• JWT + API Key Auth - Flexible authentication options
• OAuth - GitHub and Google sign-in
• Usage Tracking - Monitor API usage per user
• Streaming - Real-time streaming responses via SSE

Tech Stack

• Runtime: Node.js + TypeScript
• Framework: Express.js
• Database: PostgreSQL + Prisma ORM
• Cache: Redis (optional)
• Auth: JWT + bcrypt
• AI: OpenAI SDK, Anthropic SDK
• Deployment: Docker, Docker Compose

Quick Start

Using Docker Compose (Recommended)

git clone https://github.com/chatroutes/chatroutes-backend.git
cd chatroutes-backend

# Set up environment
cp .env.example .env
# Edit .env with your API keys (OpenAI, Anthropic, etc.)

# Start everything
docker-compose up --build

The API will be available at http://localhost:3000.

Manual Setup

# Prerequisites: Node.js 18+, PostgreSQL 15+

# Install dependencies
npm run setup

# Set up environment
cp .env.example .env
# Edit .env with your database URL and API keys

# Run database migrations
cd services/api-gateway
npx prisma migrate dev
npx prisma generate
cd ../..

# Start development server
npm run dev

API Overview

Base URL: http://localhost:3000/api/v1

Authentication

# Register
curl -X POST http://localhost:3000/api/v1/auth/register \
  -H "Content-Type: application/json" \
  -d '{"email": "user@example.com", "password": "yourpassword", "name": "Your Name"}'

# Login
curl -X POST http://localhost:3000/api/v1/auth/login \
  -H "Content-Type: application/json" \
  -d '{"email": "user@example.com", "password": "yourpassword"}'

Conversations

# Create a conversation
curl -X POST http://localhost:3000/api/v1/conversations \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"title": "My Conversation", "model": "gpt-4o"}'

# Send a message
curl -X POST http://localhost:3000/api/v1/conversations/:id/messages \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"content": "Hello!", "role": "user"}'

Branching

# Create a branch from any message
curl -X POST http://localhost:3000/api/v1/conversations/:id/branches \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"forkPointMessageId": "MESSAGE_ID", "name": "Alternative approach"}'

See documentation/api/ for the complete API reference.

Environment Variables

Key variables (see .env.example for the full list):

Variable	Description	Required
DATABASE_URL	PostgreSQL connection string	Yes
JWT_SECRET	Secret for JWT token signing	Yes
OPENAI_API_KEY	OpenAI API key	For OpenAI models
ANTHROPIC_API_KEY	Anthropic API key	For Claude models
REDIS_URL	Redis connection URL	No (optional cache)
PORT	Server port (default: 3000)	No

Project Structure

chatroutes-backend/
├── services/
│   └── api-gateway/         # Main application
│       └── src/
│           ├── routes/      # API endpoints
│           ├── services/    # Business logic
│           ├── middleware/  # Auth, rate limiting
│           ├── config/      # Configuration
│           └── prisma/      # Database schema
├── tests/                   # Test suite
├── documentation/           # API docs, architecture
├── deployment/              # Docker, infrastructure
├── docker-compose.yml       # Local development stack
└── .env.example             # Environment template

Development

npm run dev          # Start dev server
npm run build        # Build TypeScript
npm test             # Run tests
npm run lint         # Lint code

Contributing

See CONTRIBUTING.md for guidelines.

License

MIT