Locally Talk with your private documents, and even do a private research without any tokens concerns

A pure Python implementation of ReAct agent without using any frameworks like LangChain. It follows the standard ReAct loop of Thought, Action, PAUSE, and Observation. The agent utilizes multiple tools, including Calculator, Wikipedia, Web Search, and Weather. A web UI is also provided using Streamlit.

AVA is an AI-driven voice assistant designed to facilitate natural, real-time conversations through speech. It leverages automatic speech recognition (ASR), natural language understanding (NLU), and text-to-speech (TTS) synthesis to understand user input, process queries intelligently, and respond with human-like voice output.

A hybrid Research Assistant that combines an exact Knowledge Graph (Neo4j) with a Retrieval‑Augmented Generation pipeline (FAISS + Cross‑Encoder + FLAN‑T5) behind a sleek Streamlit interface.

🤖 CLI LeetCode agent. Semantic search + your history = personalized problem selection and guidance.

“A graph-based Retrieval-Augmented Generation (RAG) agent built with LangGraph and Ollama. It performs query rewriting, vector search, relevance checking, and answer generation using a fully automated pipeline.”

A local RAG (Retrieval-Augmented Generation) system that allows you to upload PDFs and have conversations about their content using local LLMs via Ollama.

Multimodal Voice RAG Agent using Speech-to-Text, FAISS Search, and Text-to-Speech

A Retrieval-Augmented Multi-Agent Framework for Fundamental Company Analysis and Financial Insight

Deep Research Multi-Agent System with RAG via Human In The Loop

A RAG agent for uploading and finding information about projects in a knowledge base

simple rag agent that queries, analyses and extract meaningful info from document. stores and retrieves from qdrant vector db.

Designed a RAG-Agent with search capability which can help company employees regrading their data policy related work