🛡️ Multimodal deepfake detection & explainable AI digital forensics workstation. Features video/audio late-fusion classifiers, Grad-CAM visual heatmaps, and an offline forensics RAG agent.

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.

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

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.

🏆 Dell Cloud Native Award Champion, Agent M

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.”

Nền tảng RAG và SDLC Agent chạy cục bộ bằng Docker Compose, tích hợp Ollama, Qdrant, Neo4j, Open WebUI và workflow 15 AI agents để ingest tài liệu, hỏi đáp tri thức và tự động hóa phân tích, thiết kế, sinh code.

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

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

Snippet of the RAG Agent created via Terminal. It can answer any question related to RAG (1) and (2)The first two images shows random questions being answered by me to my RAG Agent related to Vector Database, RAG agent and how RAG agent works in the background to understand contextual text breaking them to chunks of few characters which are then co

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

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

A specialized RAG-powered AI agent for querying the 2026 FIA Formula 1 Technical Regulations with precise Article Number citations and a dual CLI/Streamlit interface.

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

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