Credits

Industry-leading React framework providing Server-Side Rendering (SSR), Static Site Generation (SSG), Incremental Static Regeneration (ISR), built-in routing, API Routes, and image optimization - the best choice for modern web development.

Declarative, component-based JavaScript UI library developed by Meta (Facebook), offering excellent performance through virtual DOM and efficient update mechanisms, with a vast ecosystem and community support.

JavaScript superset developed by Microsoft, adding static type system and latest ECMAScript features, providing better development experience, code hints and error checking, greatly improving maintainability and efficiency.

Revolutionary utility-first CSS framework for rapidly building custom designs through composing utility classes, with built-in responsive design, dark mode and JIT compiler, dramatically improving development speed while keeping CSS lean.

Internationalization solution designed for Next.js App Router, supporting server and client components, message formatting, plural forms, date/time localization, with complete multi-language support and excellent type safety.

Industry-standard MySQL driver for Node.js, providing fast and reliable database connections. Supports Promise/async-await, connection pooling, and Prepared Statements for SQL injection prevention. This project uses it as the primary database interface for storing and querying user data, game records, blog posts, and more.

Modern high-performance web framework focused on developer experience and application speed. Features powerful plugin system, JSON Schema validation, and automatic API documentation. Both AI Core and RAG Ingestor services use Fastify as their API server to handle AI conversations, RAG queries, and backend logic.

Industry-leading framework for building LLM applications, simplifying AI development workflows. Provides unified interfaces for integrating various LLMs, vector databases, tools, and memory systems. This project uses LangChain to build RAG (Retrieval-Augmented Generation) systems for intelligent document Q&A and content generation.

Lightweight local LLM runtime environment enabling developers to run large language models on their machines. Supports open-source models like Llama 3, Gemma, and Mistral. This project uses Ollama as the AI inference engine for fully offline AI conversations, ensuring user privacy and data security.

High-performance embedded vector database designed for AI applications. Built on Apache Arrow and Lance format for ultra-fast vector similarity search. This project uses LanceDB to store document vector embeddings, powering RAG system semantic search to quickly find content most relevant to user queries.