RecoMe — Personalized Recommendation Engine
Personal interest-graph and agentic recommendation engine turning cross-platform activity into a typed Neo4j interest graph with SSE-streamed recommendations.
Each file is a shipped operation — voice and RAG platforms, distributed backends, ML pipelines. Click OPEN FILE on any record for mission outcomes.
Personal interest-graph and agentic recommendation engine turning cross-platform activity into a typed Neo4j interest graph with SSE-streamed recommendations.
AI meeting-intelligence platform automating pre-meeting research, live in-meeting assistance, and post-meeting synthesis with real-time voice and hybrid RAG.
Document-ingestion system whose centerpiece is automatic context routing — embedding-similarity decides whether to extend an existing knowledge bucket or create a new one.
Knowledge-graph retrieval engine that minimises LLM calls by doing entity resolution and validation in embedding and rule space; concepts live in hyperbolic (Poincaré) geometry.
Multi-agent conversational AI with specialized agents for research, coding, and task automation.
Next-door chatbot with Google Gemini API integration and real-time sentiment detection.
End-to-end MERN + TypeScript app for live stock trading with GraphQL and WebSocket feeds.
ML-powered fraud detection pipeline using Isolation Forest and One-Class SVM with 95%+ accuracy.
Real-time team collaboration platform integrating chat, task management, and video conferencing.
Tool to analyze and detect biases in Large Language Model outputs across different demographics.
SaaS chatbot platform with customizable AI agents, analytics, and multi-channel integration.
Automated ML pipeline for data preprocessing, cleaning, and intelligent feature selection.
Modern weather app with real-time forecasts, location-based alerts, and interactive visualizations.