Projects
A collection of projects showcasing my work in machine learning and AI, and web development. As well as open source contributions.
Morgana Deep Research Agent
An autonomous research studio that transforms open-ended questions into publication-ready briefs, reports, and media packages by orchestrating planning, deep web intelligence, critique, and polished synthesis.
SportSphere AI Agent
A conversational AI agent/assistant for sports enthusiasts, providing real-time information on MLB, NBA and Global Soccer. Interact via voice or text to get live scores, team rosters, player statistics, and league standings.
Pocket Traveler
Pocket Traveler is an AI-powered personal travel assistant that creates fully customized itineraries based on your preferences. Input your travel details (origin, destination, dates, and more) via text or voice, and Pocket Traveler handles the rest, generating personalized flight options, accommodation suggestions, activities, dining recommendations, local insights, and even safety tips. The complete itinerary is delivered directly to your inbox.
CustomGPT
CustomGPT is a versatile LLM chatbot built with Streamlit that integrates multiple language models (OpenAI, DeepSeek, HuggingFace, and Ollama) and implements Retrieval-Augmented Generation (RAG) techniques (both Simple RAG and LightRAG). It supports various RAG operations, including document uploads, web link analysis, GitHub repository context, and research paper integration. It utilizes Pinecone and Chroma for vector databases and stores chat history in MongoDB.
License Plate Detection
A Streamlit-powered application for license plate detection using YOLOv8. The app allows users to upload images or videos, and it detects and highlights license plates within the provided media. The training data was sourced from Roboflow.
AI Vision Inspector
A browser-based visual QA assistant that lets teams drop an image, run Roboflow object detection, and have OpenAI narrate every finding with confidence scores and zoomable crops—all without exposing API keys.
langsmart-bigtool
A Python library that equips LangGraph agents with a two-stage, LLM-driven tool selector so they can scan massive registries, pick the right skills, and execute the task without maintaining vector stores.
NBA MCP Server
A Model Context Protocol service that exposes live NBA scoreboards, play-by-play feeds, player stats, and team analytics so any Claude-compatible agent can tap professional basketball data in real time.
Soccer MCP Server
A football intelligence bridge for Claude-compatible agents, delivering live match timelines, league tables, player profiles, and fixture analytics across global competitions through the API-Football platform.
Ovarian Cancer ML Classification
This project applies machine learning techniques to classify ovarian cancer stages, aiming to aid in early detection and personalized treatment strategies. Predictive models are trained using patient data and biomarkers to accurately identify cancer subtypes.
Unravelling the Challenges of Unemployment in Africa
A data-driven analysis of unemployment in Africa, exploring regional disparities, gender differences, and the impact of factors like education funding, private sector growth, and infrastructure development. This project was an entry for the 10Alytics Hackathon 2023.
Sentiment Analysis of Digital Lending Platforms in Nigeria
This project performs sentiment analysis on customer reviews of six digital lending platforms in Nigeria (Quickcredit, Carbon, Newcredit, Fairmoney, Branch, and Palmcredit) collected from the Apple App Store and Google Play Store. Inspired by a Premium Times article on data privacy breaches, the project uses machine learning and natural language processing (NLP) to gauge customer sentiment towards these services.
Tackling the Health Crisis in Africa
A data analysis project focused on improving health outcomes in Africa. The project explores data related to major causes of death, including cardiovascular diseases, HIV/AIDS, and malaria, to identify trends and provide insights for addressing these health challenges. This project was created for the 10Alytics Hackathon in 2023.