OpenGateway AI is an API gateway that lets you integrate multiple AI providers through a single, consistent endpoint. Switch between OpenAI, Anthropic, Google, Groq, and more without changing your application code.

• Multi-Provider Support: OpenAI, Anthropic, Google, Groq, and more
• Unified Interface: One API shape for all providers (OpenAI-compatible)
• Streaming Support: Real‑time streaming for chat completions
• Smart Routing: Load balancing and failover (provider‑aware)
• Cost Optimization: Choose models by cost and performance
• Enhanced Authentication:
  • JWT with refresh tokens (httpOnly cookie or token in body)
  • Email verification
  • Password reset
  • Secure API key generation and management
• Rate Limiting: Tier‑based usage protection
• Analytics & Monitoring: Comprehensive usage and cost analytics
• Modern UI/UX:
  • Refined landing page and dashboard
  • Auth pages (login/register/forgot/reset) redesigned
  • Authenticated Playground page (moved out from landing)
• Usage Tracking: Monitor tokens, latency, and costs

• Modern Chat UI (Next.js 14 + Tailwind CSS): ChatGPT-like layout with polished navbar, sidebar rooms, and message area.
• Database-backed Chat Rooms & Messages: Persist rooms and messages in PostgreSQL via Prisma.
• Dynamic Model Selection per Room: No fixed modelId at room creation; user picks model per room (stored via localStorage).
• State Management with TanStack Query: Hooks for models, rooms, and messages with proper caching and loading states.
• Real-time Messaging (WebSockets with Hono/Bun): Join/leave rooms, typing indicators, and broadcast new messages.
• Message Search: Local and server-side search with highlighted results.
• File Attachments: Upload and send multiple attachments with messages; rich preview in UI.
• CORS & Auth Improvements: Correct preflight handling, credentialed requests, and wider allowed headers/methods.

• Framework: Hono + Bun (Node-compatible)
• Database: PostgreSQL via Prisma ORM
• Cache: Redis
• Auth: JWT + Refresh tokens + API Keys + Optional 2FA
• Rate Limiting: Redis-based
• Realtime: WebSockets via hono/bun upgrade helper

• Framework: Next.js 14
• Styling: TailwindCSS
• State: TanStack Query
• UI: Custom components + Heroicons
• Hooks: useModels, useChatRooms, useRoomModelSelection, useWebSocket, useDebounce

• Bun runtime
• PostgreSQL
• Redis
• Node.js 18+ (for frontend)

1. Clone repository

git clone https://github.com/zakirkun/OpenGateway-ai.git
cd OpenGateway-ai

2. Install dependencies

bun install

3. Setup environment variables

# Backend
cp packages/backend/env.example packages/backend/.env
# Edit packages/backend/.env with your settings

# Frontend
cp packages/frontend/.env.example packages/frontend/.env.local
# Edit packages/frontend/.env.local with your settings

4. Setup database

cd packages/backend
bunx prisma db push
bunx prisma generate

5. Start development servers

# Terminal 1 - Backend
cd packages/backend
bun run dev

# Terminal 2 - Frontend
cd packages/frontend
bun run dev

# Start all services
docker-compose up -d

# View logs
docker-compose logs -f

# Stop services
docker-compose down

# Database
DATABASE_URL="postgresql://username:password@localhost:5432/OpenGateway_ai"

# Redis
REDIS_URL="redis://localhost:6379"

# JWT
JWT_SECRET="your-super-secret-jwt-key"

# AI Provider API Keys
OPENAI_API_KEY="sk-your-openai-key"
ANTHROPIC_API_KEY="sk-ant-your-anthropic-key"
GOOGLE_API_KEY="your-google-api-key"
GROQ_API_KEY="gsk_your-groq-key"

# Server
PORT=3001
NODE_ENV="development"
# CORS
# Comma-separated list of allowed origins in dev
CORS_ORIGIN="http://localhost:3000,http://127.0.0.1:3000"

NEXT_PUBLIC_API_URL="http://localhost:3001"

Requests to protected endpoints require an Authorization header:

Authorization: Bearer YOUR_API_KEY

curl -X POST http://localhost:3001/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ],
    "max_tokens": 1000,
    "temperature": 0.7,
    "stream": false
  }'

curl -X POST http://localhost:3001/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-3-5-sonnet-20241022",
    "messages": [
      {"role": "user", "content": "Tell me a story"}
    ],
    "stream": true
  }'

curl -X POST http://localhost:3001/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/dall-e-3",
    "prompt": "A beautiful sunset over mountains",
    "n": 1,
    "size": "1024x1024"
  }'

curl -X POST http://localhost:3001/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  -F "model=openai/whisper-1"

curl -X GET http://localhost:3001/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Notes on model objects:

• Response uses owned_by and display_name at the top level, e.g.

  {
    "id": "openai/gpt-4o",
    "owned_by": "OpenAI",
    "display_name": "GPT-4o"
  }

• Server exposes REST endpoints for rooms and messages (see API.md), including:
  • Create/update/delete/archive rooms
  • List messages with optional search query param
  • Create messages with optional attachments
  • Global message search endpoint

Powered by hono/bun upgrade helper. Events include:

• join_room, leave_room for presence
• typing indicator per user/room
• new_message broadcast to room members

• openai/gpt-4o - GPT-4o
• openai/gpt-4o-mini - GPT-4o Mini
• openai/gpt-3.5-turbo - GPT-3.5 Turbo

• anthropic/claude-3-5-sonnet-20241022 - Claude 3.5 Sonnet
• anthropic/claude-3-5-haiku-20241022 - Claude 3.5 Haiku
• anthropic/claude-3-opus-20240229 - Claude 3 Opus

• google/gemini-1.5-pro - Gemini 1.5 Pro
• google/gemini-1.5-flash - Gemini 1.5 Flash

• groq/llama-3.1-70b-versatile - Llama 3.1 70B
• groq/llama-3.1-8b-instant - Llama 3.1 8B
• groq/mixtral-8x7b-32768 - Mixtral 8x7B

OpenGateway AI provides a comprehensive analytics dashboard:

• Usage Statistics: Total requests, tokens, dan biaya
• Performance Metrics: Latency dan error rates
• Provider Comparison: Perbandingan performa antar provider
• Cost Analysis: Analisis biaya per provider dan model
• Real-time Monitoring: Monitoring real-time untuk semua request

• API Key Authentication: Secure API key system
• Rate Limiting: Abuse & DDoS protection
• Input Validation: Strict schema validation
• Error Handling: Safe errors without leaking sensitive data
• CORS Protection: Tight CORS configuration

1. Setup production environment

# Set environment variables
export NODE_ENV=production
export DATABASE_URL="your-production-db-url"
export REDIS_URL="your-production-redis-url"
# ... other production variables

2. Build and deploy

# Build backend
cd packages/backend
bun run build

# Build frontend
cd packages/frontend
bun run build

# Deploy using your preferred method (Docker, PM2, etc.)

# Build production images
docker-compose -f docker-compose.prod.yml build

# Deploy
docker-compose -f docker-compose.prod.yml up -d

1. Fork repository
2. Create feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/amazing-feature)
5. Open Pull Request

Distributed under the MIT License. See LICENSE for more information.

# Setup 2FA
POST /auth/2fa/setup

# Verify and enable
POST /auth/2fa/verify
{
  "token": "123456"
}

# Check status
GET /auth/2fa/status

# Disable 2FA
POST /auth/2fa/disable
{
  "token": "123456"
}

# Login (may require 2FA)
POST /auth/login
{
  "email": "[email protected]",
  "password": "password123",
  "twoFactorCode": "123456"  # Optional, required if 2FA enabled
}

• Email verification on registration
• Password reset emails
• 2FA setup notifications
• Usage alerts
• Security notifications
• Welcome emails

Configure SMTP dalam .env:

SMTP_HOST="smtp.gmail.com"
SMTP_PORT=587
SMTP_USER="[email protected]"
SMTP_PASS="your-app-password"
FROM_EMAIL="noreply@your-host"
FROM_NAME="OpenGateway AI"

WEBHOOK_URL="https://your-app.com/webhooks/OpenGateway"
WEBHOOK_SECRET="your-webhook-secret"

SLACK_WEBHOOK_URL="https://hooks.slack.com/services/..."

DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."

• Profile management
• Subscription tier information
• Usage monitoring
• Email verification status

• Create/revoke API keys
• Usage tracking per key
• Last used timestamps
• Secure key display
• New: Copy button and creation modal feedback

• Enable/disable 2FA
• QR code generation
• Backup codes management
• Security status

• Real-time usage stats
• Cost analysis
• Provider performance
• Historical data

• Modern navbar with profile dropdown
• Sidebar with rooms (active/archive, title edit, delete)
• Dynamic per-room model selection
• Message list with streaming, typing indicator
• File attachments (upload + preview)
• Local and server-side search
• Responsive and mobile-friendly

• Issue Streaming on Chat Interface
• Need Enhance the Chat Components

• Documentation: Docs
• Email: [email protected]
• Discord: Join our community
• GitHub Issues: Report bugs

• OpenAI for powerful API
• Anthropic for Claude models
• Google for Gemini models
• Meta for Llama models
• Groq for fast inference
• Hono team for an excellent framework
• Next.js team for an amazing React framework