Transforms dense research papers into clear visual explanations and structured insights within seconds. Designed to make complex ideas intuitive by turning long-form technical content into easily graspable understanding.

A vector database built from scratch to power semantic search and retrieval without external dependencies. Implements embedding storage, similarity indexing, and fast cosine search to understand and recreate the core infrastructure behind modern LLM and RAG systems.

An end-to-end on-device LLM implementation using TinyLlama, enabling offline conversational AI through optimized mobile inference pipelines and efficient resource utilization.

Real-time flight tracking system that monitors aircraft activity around Pune Airport with intelligent notifications.

Transform API documentation into conversational experiences. Chat with your APIs naturally and get instant, context-aware responses.