Scalable agent registry for AI agents using A2A protocol AgentCard with semantic search. AWS serverless (Lambda, S3 Vectors, Bedrock). Python SDK & React Web UI.

MedSage is a multimodal healthcare assistant that combines LLMs, vector search, and real-time reasoning to deliver fast, reliable medical insights. It supports symptom analysis, medical document Q&A, universal file RAG, multilingual interactions, and emergency SOS with live location.

Pure-Python, zero-dependency RAG memory engine for conversational AI. Retrieves semantically relevant messages from conversation history using two-phase retrieval, TF-IDF + concept-overlap scoring, narrative element extraction, and bidirectional typo correction. No embeddings or vector DB required.

Terminal-based semantic code search. Local, no API keys, live re-indexing

A functionally operational, mathematically unhinged system for achieving 10× effective memory amplification on Apple Silicon using quantized fractal compression, complex-plane KV decomposition, and Euler-aligned swap geometry.

An end-to-end RAG system that grounds LLMs in factual reality, using semantic search on real-time news to provide verifiable, context-aware answers.

DigiBrain is a second brain web platform that stores links (tweets, YouTube videos, documents, etc.) enriched with metadata such as title, description, and tags. The system integrates an AI assistant that retrieves contextually relevant content using embeddings and a vector database.

Building production-grade Retrieval-Augmented Generation (RAG) systems. Explore advanced chunking strategies, hybrid search with Weaviate, LLM task orchestration, and fine-grained generation control.

Hybrid RAG with three retrievers—Lexical (BM25), Semantic (embeddings), and Hybrid (Reciprocal Rank Fusion) — parallel retrieval, Llama 3 generation, and side-by-side evaluation with reproducible notebooks.

SementicCore: A transformer-based text embedding model trained with contrastive learning (SimCSE approach) for generating high-quality sentence embeddings.

An AI-powered Fashion Assistant built using Retrieval-Augmented Generation (RAG). Combines semantic search, reranking, and LLM-based reasoning to deliver intelligent fashion recommendations, product discovery, and 24/7 customer support.

A hands-on exploration of Retrieval-Augmented Generation's core components: semantic search, retriever evaluation, and context-augmented LLM prompting.

📖 A Retrieval-Augmented Generation (RAG) MCP server for markdown documentation with semantic search capabilities

"When memories are scattered... always leads to DreamTheater awakens",, "We take photos to stop time. DreamTheater takes photos to make time flow again."

An experiment around figuring out best way to provide code context to coding agents

A local-first, privacy-focused personal context engine that lets you chat with your documents using offline AI models. Built with Electron, Python, and Ollama.

Fetch all the details from given url and user can get accurate responses to the given question.

Production RAG system for automated enterprise support using Vertex AI embeddings, Neo4j knowledge graphs, and LangChain/LangGraph agentic workflows. Achieves 95%+ accuracy through semantic search, multi-hop reasoning, and confidence-based escalation with comprehensive evaluation frameworks.

An AI-powered document assistant that lets you "chat" with your PDFs using Retrieval-Augmented Generation (RAG) and local LLMs

Hybrid semantic retrieval and recommendation system combining collaborative filtering (SVD) with RAG, transformer embeddings, and FAISS for intelligent search and ranking.