Data agents

An advanced AI-powered solution enhances network diagnostics by leveraging large language models (LLMs). It parses various logs to identify patterns and anomalies, providing actionable insights for diagnosing and resolving network issues efficiently. This simplifies analysis, enabling quicker and more accurate problem detection and resolution.

Visual RAG Project Generator - Create customized Retrieval-Augmented Generation projects in minutes. Part of the AI Training Program by Upgrade Hub & CSIC.

This project is designed to be your intelligent assistant in the often challenging journey of job hunting. JobFlowAI helps you streamline your job search, optimize your resumes, and prepare for interviews using our suite of AI-powered tools.

This is our project which we completed in 24 hours for Dragon Hackathon in University of Ljubljana. Project includes, network analysis, streamlit, LLM to build a chat bot and prompt engineering.

Multi-agent AI ecosystem for automated financial auditing and fraud detection using CrewAI. Features DuckDB-powered ETL pipelines and orchestrated LLM agents for risk-based reporting. Converts raw financial data into verified, human-level audit reports with compliance validation.

An intelligent AI-powered system that automatically extracts professional data from LinkedIn profiles and generates tailored, professional resumes using CrewAI's multi-agent framework.

AI-powered research with human guidance and citation integrity

This project utilizes a multi-agent system powered by crewAI to monitor, analyze, and strategize in the financial markets, specifically focusing on stock trading. Each agent in the system specializes in a unique aspect of trading, working together to provide comprehensive insights and actionable strategies.

This project demonstrates a multi-agent system built using AutoGen and Groq's LLaMA 3 model, designed to automate the analysis of Apple (AAPL) stock's daily closing prices over the past month. The system utilizes a collaborative architecture involving multiple AI agents—each assigned a specific role in the data analysis pipeline.

Powered NLP with LLMs

Foundation for a Scalable, Production-Ready Multi-Agent AI Intelligence System. Establishes core orchestration, robust service integrations, and resilient data architecture—paving the way for a full-spectrum, autonomous AI platform ready for advanced intelligence, analytics, and automation.

Multi-Agent Orchestrator System (MOS) is a real-time, multi-agent monitoring and management system that supports multiple platforms.

Stream fleet, customs, rail, and carrier telemetry/metadata as unified low latency event spans.

A research-grade, local-first multi-agent AI framework for rigorous scientific analysis, combining symbolic mathematics, numerical methods, and RAG-based document intelligence with reproducible execution

An agentic Real Estate search experience on Couchbase Capella that personalizes property discovery with vector search and long term memory.

This repository provides a streamlined solution for performing patent similarity searches by leveraging the capabilities of Language Learning Models (LLMs) and Retrieval-Augmented Generation (RAG). The application integrates advanced tools such as Google Patent Database, DuckDuckGo search, and cutting-edge models like Google's Gemini

393 AI-generated research artifacts produced by Enoch with provenance metadata, evidence bundles, claim-ledger files, and public audit reports.

open source deep research

Demo of a smartwatch based systematic health monitoring solution designed for patients with chronic conditions

Operationalizes PM insights through working agents grounded in GRC best practices. Provides prompt libraries and tools to identify governance and compliance risks before scaling programs, analytics initiatives, or AI systems.

🔍 Create AI experts on-demand for multi-agent conversations with real-time web research and intelligent context management.

VM for AI

PlotAgent().set_df(df).process_message("plot this df in the best way you can think of").get_figure().show()

Genesis: Multi-Modal Agentic AI for Cancer Variant Effect Prioritization

Light-weight research-grade framework for creating multi-stage GPT-5 agentic pipelines with custom tooling. Achieved a 1st Place Weekly Result in FutureX competition.

Experimenting with new agent frameworks and hosting cutting-edge research papers, all open-source.

AI-based program for data analysis and processing

libcommbase is a collection of libraries to centralize common functions that can be shared across multiple conversational AI assistant projects. It operates offline and can be implemented with AI (ML/DS) and programming languages

🤖 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

KodaAI is a performance analytics platform that quantifies the efficiency gains provided by AI-assisted development using Kiro. It bridges the gap between human estimation (Jira) and machine-accelerated output (GitHub/Kiro) to calculate a "Speed Multiplier" for software teams.

Bot para Telegram que monitora valores de Bitcoin e Litecoin no MercadoBitcoin e Bitcoin na Xapo (em USD).

Restaurant Chat Bot App! This application is built using Flutter and is designed to provide an interactive and intuitive chat experience for restaurant customers. Whether you're looking to browse the menu, make a reservation, or get answers to your questions, our chat bot is here to help.

Next.js Full Stack App. Build ChatGPT-like chatbots for your data. Easily organize files in folders

AI-powered medical clinic chatbot using Model Context Protocol (MCP) with Google Gemini AI. Features appointment management, clinic information retrieval via ChromaDB vector search, and a responsive React frontend. Built with Node.js, MongoDB, and MCP Server architecture.

📰News + 📱Messenger. Take your news everyday by chatting.

Emotion-aware AI companion designed for natural, human-like conversation. TalkSpace combines machine learning, LLMs, and real-time UI adaptation to create a calm, supportive space where users feel heard — not analysed 🌿

A Facebook Messenger AI Chatbot using Vietnamese (Scientific Research 2021)

Simple mass communication chatbot for skype, with database connection and routine support.

This Repo contains Mary ChatBot a trained Model containing a story, query and answers. Trains the story and query to output the correct answer. It uses the Softmax activation layer for multiclass classification

RAG chatbot built on top of trending M&A news.

Aide advanced virtual artificial intelligence assistant. Also capable of controlling and being the brain of advanced humanoid robots. This repository contains chat data for Aide.

A chatbot interface for retrieving Meraki network data and analysis with natural language!

Some of my NLP projects I've worked on and to harden my experience with the research field of NLP.

A Machine-Learning-based chatbot platform with data analytics tools developed with Django

A task oriented chat bot based on the MultiWOZ dataset and implemented using the RASA framework

CureWise-AI is a modern, production-grade healthcare data platform that leverages Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and advanced AI/ML techniques to deliver intelligent analytics, medical report parsing, and conversational AI for hospitals, doctors, and patients.

This is a chatbot to execute Khiva algorithms using natural language.

Pass your custom template and you are ready to use your own bot.

Sentiment Analysis app with React-Native

An LLM-based chatbot for analyzing Excel documents using DeepSeek R1 reasoning model

A simple artificial intelligence.

Vercel AI SDK, Next.js, and OpenAI Chat Example

Chatbot app for interactively conversing with PDFs

a demo of a chatbot for querying and interpreting biomodels stored in the VCell BioModel Database. It enables users to interact with biological modeling resources using natural language and provides structured outputs, model metadata, downloadable files, and visualizations in real time.

Open-Ended AI Chatbot built with Node.js, Ollama, and open-source LLMs (Mistral / Mixtral). This project provides a simple chatbot server with a lightweight web UI, designed for extension with rules, database integration, and custom website widgets.

An AI-driven healthcare assistant that predicts diseases based on user-provided symptoms. This project leverages machine learning for disease prediction, provides descriptions and precautionary measures, and includes a user-friendly GUI with text-to-speech integration.

Collection of NLP Examples

Context-aware chatbot using LLaMA 3.1 embeddings and a vector database for efficient query understanding and response generation, with NLP techniques like entity extraction and intent recognition.

Flask/LLM based meeting summarization tool

🎤 Transform any browser tab into an intelligent audio recording system with automated transcription and AI analysis via n8n. Works with Zoom, Meet, Teams, YouTube, Spotify, Discord & more!

Ask any questions about data in an SAP table in Microsoft Teams.

Financial Analyst | Assistant AI.

AI Resume Analysis with n8n

A benchmark study analyzing cost and token efficiency across 14 LLMs from 5 providers — comparing price-per-token, latency, and accuracy to surface the most cost-effective models for real-world use.

This project demonstrates how to evaluate the use of LLMs and SLMs for extracting structured data from documents using .NET

This project is dedicated to building an intelligent data processing pipeline using AutoChain LLM and BERT ML.

This collection includes jailbreak prompts utilized in different LLMs for research objectives. The outcomes of our study are detailed in the research paper named "RogueGPT: Unleashing Jailbreak Prompts on LLMs."

Building a GPT-3 powered Amazon Support Bot for precise customer query responses via fine-tuned model on Amazon QA data

High-performance MCP server for log analysis. Give Claude the ability to analyze massive log files with SIMD-accelerated parsing. 5-50x faster than awk for aggregations.

Turn your MacBook notch into a live Claude AI usage monitor — Dynamic Island-style, native Swift, zero telemetry.

AI-powered health platform with multi-LLM engine (GPT-4o, Claude, Gemini). Workout generation, medication tracking with OCR, vision AI, gamification with leaderboards/rewards. Self-hosted, privacy-first.

A TypeScript-based autonomous agent framework with modular systems for memory, planning, and tool integration. Features vector-based recall, multi-strategy planning, and extensible tools for AI agent development.

Real-time Claude AI usage monitor for Windows — hover the tray, see your session, weekly, and monthly limits.

Demo of uv for a streamlined Python package management experience

Smart Search with GenAI is an AI-powered semantic search tool that delivers context-aware, summarized answers to natural language queries over structured data. It leverages Streamlit, FAISS, and Azure OpenAI for efficient vector search and LLM-based summarization.

An entire RAG (Retrieval-Augmented Generation) pipeline library designed to streamline the integration of language models with retrieval systems. ragyphi can extract text, table and image data from your pdf files and uses clever llm-based summarization techniques to augment the extracted data for efficient retrieval.

[Experimental] Open-source RAG System for diverse document types

Platform for RAG with NASA data for managing data on exoplanets for Nasa Space App Challenge 2025.

EarningsAI Demo is a powerful tool that combines audio transcription, document processing, and AI-powered analysis to help users extract insights from earnings calls and financial documents. Built with Fireworks AI and MongoDB, it provides both a command-line interface and a web application for processing and querying financial data.

RAG agent with SGR, smart indexing and reranking, metadata enrichment, parent document extraction

BigQuery Semantic Search Orchestrator

RAG-optimized documentation and data sources for AI-native development on the Flow network. Ground LLMs in accurate Flow and Cadence context.

Repo for DermAssist: Your AI Assitant for Skin Problems. Powered by a vision model and a reliable RAG system.

Retrieval Pivot Attacks in Hybrid RAG (Vector → Graph)

*Built upon the integration of text, image, and audio modalities, this Multi-modal RAG task follows a structured, step-by-step pipeline to effectively combine and process diverse data sources.*

RAG - Ops: RAG with Operations. We help you to deploy RAG with changing in datasources.

A Jupyter Notebook–powered toolkit that uses Retrieval-Augmented Generation (RAG) to help you craft a knockout resume. Feed it your raw career data (LinkedIn exports, old CVs, brag-worthy project notes), and let an AI do the heavy lifting—so you can spend your time practicing interview answers (or napping).

Data Pipeline with validation + AI Assistant

A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.

Turn any LLM into a self-extending knowledge agent powered by a graph-structured memory - complete with PDF-to-graph ingestion, budget-aware optimisation, and dual-engine orchestration.

Native macOS personal knowledge base with AI — LightRAG knowledge graph, RAG chat, SpriteKit graph viewer, MCP bridge, 6 LLM providers. Privacy-first: your data stays local.

NLP + RAG technique for requirements engineering.

Moved to github.com/vanedb/vanedb (cpp/) — archived

Practical sessions for the “Data Science for Economics” at the CEMFI Summer School 2025.

Insightic is a comprehensive digital forensics platform with MongoDB-based case management, real-time map visualization, and AI-powered analysis capabilities.

Python client for Eclipse RDF4J — interact with RDF4J repositories, execute SPARQL queries, and manage RDF data seamlessly in Python.

RAG Backend for Aleph Alpha LLMs.

Rust CLI tool to interact with Ollama with Surreal DB Vector Database

Retreival-Augmented Generation with Mixtral 8x7b powered by MILVUS vector database with semantically chunked text embeddings retreived and reranked using BGE-M3.