VTChat

A modern, privacy-first AI chat application with enterprise-grade security

Live Demo | Documentation | Security Guide

---

🚀 Overview

VTChat is a production-ready, privacy-focused AI chat application delivering cutting-edge AI capabilities through a sophisticated dual-tier subscription system. Built with modern web technologies and a privacy-first architecture, VTChat offers advanced AI reasoning, document processing, web search integration, and comprehensive multi-AI provider support.

✨ Key Features

🧠 Advanced AI Capabilities

• Reasoning Mode (VT+ exclusive): Complete AI SDK reasoning tokens support with transparent thinking process
• 9 Free AI Models: Gemini 2.0/2.5 Flash series + OpenRouter models (DeepSeek V3, DeepSeek R1, Qwen3 14B)
• Multi-AI Provider Support: OpenAI, Anthropic, Google, Fireworks, Together AI, and xAI integration
• Document Processing (VT+ exclusive): Upload and analyze PDF, DOC, DOCX, TXT, MD files (up to 10MB)
• Structured Output Extraction (VT+ exclusive): AI-powered JSON data extraction from documents
• Web Search Integration (VT+ exclusive): Grounding capabilities with real-time information
• Mathematical Calculator: Advanced functions including trigonometry, logarithms, and arithmetic

🔒 Privacy-First Architecture

• Local-First Storage: All chat data stored in browser's IndexedDB via Dexie.js
• Zero Server Storage: Conversations never leave the user's device
• Multi-User Isolation: Complete data separation on shared devices
• Enterprise-Grade Security: Secure authentication with Better Auth
• Advanced Application Security: Arcjet protection with rate limiting, bot detection, email validation, and WAF

💼 Subscription Tiers

• VT_BASE (Free): 9 AI models, calculator, basic chat, local privacy
• VT_PLUS ($10/month): All free features + reasoning mode, dark theme, web search, document upload, structured extraction
• Seamless Management: Creem.io integration with customer portal

🎨 Modern User Experience

• Shadcn UI Design System: Consistent, accessible interface
• Dark Mode (VT+ exclusive): Premium theming experience
• Responsive Design: Optimized for desktop and mobile
• 87% Performance Improvement: Faster compilation and load times

🏗️ Architecture

VTChat utilizes a Turborepo-managed monorepo structure:

vtchat/
├── apps/
│   └── web/              # Next.js 14 web application (App Router)
├── packages/
│   ├── actions/          # Server actions (e.g., feedback)
│   ├── ai/               # AI models, providers, tools, workflow logic
│   ├── common/           # Shared React components, hooks, context, store
│   ├── orchestrator/     # Workflow engine and task management
│   ├── shared/           # Shared types, constants, configs, utils, logger
│   ├── tailwind-config/  # Shared Tailwind CSS configuration
│   ├── typescript-config/# Shared TypeScript configurations
│   └── ui/               # Base UI components (from Shadcn UI)
├── docs/                 # Documentation and guides
├── memory-bank/          # Project context and evolution tracking
└── scripts/              # Utility scripts (e.g., data sync)

🛠️ Tech Stack

Frontend & Core

• Framework: Next.js 14 (App Router) with TypeScript
• Styling: Tailwind CSS + Shadcn UI design system
• State Management: Zustand + React Query
• Animations: Framer Motion
• Icons: Lucide React

Backend & Infrastructure

• Database: Neon PostgreSQL with Drizzle ORM
• Authentication: Better Auth (modern session management)
• Application Security: Arcjet protection (rate limiting, bot detection, attack prevention)
• Payment Processing: Creem.io integration
• Local Storage: IndexedDB via Dexie.js
• Deployment: Fly.io (production-ready)

Development & Build

• Runtime: Bun (package manager + JavaScript runtime)
• Monorepo: Turborepo with optimized caching
• Testing: Vitest with Testing Library
• Linting: oxlint (faster than ESLint)
• Type Checking: TypeScript with strict configuration

AI & Integrations

• AI Providers: OpenAI, Anthropic, Google, Fireworks, Together AI, xAI
• AI SDK: Vercel AI SDK with reasoning tokens support
• Document Processing: Multi-format file analysis
• Web Search: Real-time grounding capabilities

🚀 Getting Started

Prerequisites

• Bun (JavaScript runtime and package manager) - v1.1.19 or higher
• Node.js (for some Turborepo operations, though Bun is primary)
• Git for version control

Installation

1. Clone the repository:

   git clone https://github.com/vinhnx/vtchat.git
   cd vtchat

2. Install dependencies:

   bun install

3. Set up environment variables:

   cp apps/web/.env.example apps/web/.env.local

   Configure the following required variables in apps/web/.env.local:

   Essential Services:

   • DATABASE_URL - Neon PostgreSQL connection string
   • BETTER_AUTH_SECRET - Authentication secret key
   • BETTER_AUTH_URL - Authentication URL (http://localhost:3000 for development)

   AI Provider Keys (choose one or more):

   • OPENAI_API_KEY - OpenAI API access
   • ANTHROPIC_API_KEY - Anthropic Claude API access
   • GOOGLE_API_KEY - Google Gemini API access

   Payment & Subscription:

   • CREEM_WEBHOOK_SECRET - Creem.io webhook validation
   • CREEM_API_KEY - Creem.io API access
   • CREEM_PRODUCT_ID - VT Plus subscription product ID

   Security:

   • ARCJET_KEY - Application security and rate limiting
   • NEXT_PUBLIC_BASE_URL - Application base URL

4. Set up the database:

   cd apps/web
   bun run generate  # Generate database schema

5. Start the development server:

   bun dev

6. Open the application: Navigate to http://localhost:3000 in your browser.

Development Commands

# Development
bun dev                 # Start development server with Turbopack
bun build              # Build for production
bun start              # Start production server
bun test               # Run tests
bun test:coverage      # Run tests with coverage

# Code Quality
bun lint               # Lint with oxlint
bun format             # Format code with Prettier
bun format:check       # Check code formatting

# Database
cd apps/web
bun run generate       # Generate Drizzle schema

🔧 Configuration

Environment Setup

The application requires several environment variables for full functionality. Refer to apps/web/.env.example for the complete list. Key configurations include:

• Database: Neon PostgreSQL for user data and subscriptions
• Authentication: Better Auth for secure session management
• AI Providers: Support for multiple AI APIs
• Payment: Creem.io for subscription management
• Security: Arcjet for application protection

Subscription Tiers

VTChat implements a dual-tier system:

• VT_BASE: Free tier with access to 9 AI models
• VT_PLUS: Premium tier ($10/month) with advanced features

🚢 Deployment

VTChat is production-ready and deployed on Fly.io:

Production Deployment

• URL: https://vtchat.io.vn
• Infrastructure: Fly.io with 2-region setup (Singapore primary, Virginia secondary)
• Performance: 87% faster compilation, optimized bundle size
• Security: Enterprise-grade security with Arcjet protection
• Monitoring: Comprehensive error tracking and performance monitoring

Deployment Configuration

• Memory: 1GB RAM per instance
• CPU: 1 shared CPU
• Regions: Asia-Pacific (primary), USA East (secondary)
• Health Checks: HTTP and TCP monitoring
• Auto-scaling: Suspend/resume based on traffic

📚 Documentation

Production Readiness

• Production Deployment Checklist: Comprehensive pre-deployment verification
• Production Monitoring Setup: Error tracking, performance monitoring, and alerting
• Final Release Notes: Complete feature summary and achievements
• Final Project Report: Comprehensive technical and business analysis

Development & Integration

• AGENT.md: Development guidelines and conventions
• Security Guide: Comprehensive Arcjet application security implementation
• Subscription System: Plan management, caching, and Creem.io integration
• Customer Portal: User subscription management interface

Project Context

The /memory-bank directory contains contextual documents tracking project evolution, feature implementations, and development insights for continuous improvement.

🔐 Security

VTChat implements comprehensive security measures:

• Privacy-First: All conversations stored locally in IndexedDB
• Authentication: Better Auth with secure session management
• Application Security: Arcjet protection against bots, DDoS, and attacks
• Rate Limiting: Prevents abuse with intelligent rate limiting
• Data Protection: No server-side storage of sensitive chat data
• Secure Communication: HTTPS enforced, secure headers implemented

🧪 Testing

VTChat includes comprehensive testing:

# Run all tests
bun test

# Run tests with UI
bun test:ui

# Run tests with coverage
bun test:coverage

# Run specific test suites
bun test app/tests/rate-limit-simple.test.ts

Testing framework: Vitest with Testing Library for React components.

🤝 Contributing

We welcome contributions! Please follow these guidelines:

1. Fork the repository and create a feature branch
2. Follow the coding standards defined in AGENT.md
3. Write tests for new features
4. Update documentation as needed
5. Submit a pull request with a clear description

Development Standards

• Use TypeScript with strict configuration
• Follow the existing code style and patterns
• Ensure all tests pass before submitting
• Update AGENT.md with any significant changes

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

🏆 Achievements

• Zero TypeScript Errors: Complete type safety across the codebase
• 87% Performance Improvement: Optimized compilation and runtime
• Production-Ready: Deployed and running in production environment
• Security Hardened: Comprehensive protection against common threats
• Privacy-First: Industry-leading approach to user data protection

🎯 Roadmap

• Mobile app development (React Native)
• Additional AI provider integrations
• Advanced collaboration features
• Enhanced document processing capabilities
• API access for developers

---

Visit VTChat | View Documentation | Report Issues

Built with ❤️ by the VTChat team