Personal AI project manager with Claude Code integration and persistent context

🧠 LLMs don’t just process text — they read the room. Meaning emerges through context — shaped by tone, trust & trajectory. Most benchmarks flatten that. This one maps it.

🩺 Advanced multi-agent Medical AI Assistant powered by LangGraph that delivers empathetic, doctor-like responses using a hybrid pipeline of LLM reasoning, RAG from medical PDFs, and intelligent fallback tools (Wikipedia, DuckDuckGo). Features short-term memory, dynamic tool routing, and state reasoning for reliable, context-aware consultation.

The Customer Support Ticket Classification and Response System combines advance AI models with RAG to automate and elevate ticket categorisation and response generation. By leveraging multi-model integration, sentiment analysis, urgency detection, and vector-based retrieval, it delivers precise, context-aware responses and actionable insights.

Project Agora: MVP of the Concordia framework. An ethical, symbiotic AI designed to foster and protect human flourishing.

A decentralized protocol for agent trust, dialogue, and influence in open multi-agent systems.

An intelligent, context-aware Q&A backend powered by Groq LLM and Django REST Framework. Supports real-time chat, multi-turn memory, and blazing-fast responses. Seamlessly integrates with a React frontend available in a separate repo.

A stateful AI agent framework powered by the Cognitive Lattice to solve complex tasks with persistent memory and reliable tool orchestration.

🤖 NoCapGenAI is a Retrieval-Augmented Generation (RAG) chatbot built with Streamlit, Ollama, MongoDB, and ChromaDB. It features a clean, modern UI and persistent vector memory for context-aware conversations. Easily integrates with Ollama-supported models like phi3:mini, llama3, mistral, and more. Designed to support customizable assistant modes

Context-aware tool for automated BDD test generation and execution using RAG, VectorDB, and LLaMA.

A privacy-first browser extension that detects text inputs on any webpage, and generates context-aware replies using selectable LLMs.

Artificial-intuition–driven pattern recognition system under high noise & scarce data environments. Validated on real-world datasets with proven generalization, robustness & scalability.