Lionel A.

A fully-featured e-commerce platform built with Django, featuring PayPal, M-PESA, and Pay on Delivery payment options. The platform includes product variants, dynamic pricing, and a robust shopping cart system.

Streamliner-AI is a fully automated, asynchronous Python pipeline designed to monitor Kick streamers, detect viral high-energy moments, generate vertical clips optimized for social media, and publish them to TikTok without manual intervention.

An intelligent automation workflow that transforms event form submissions into beautifully formatted PDF planners using n8n, Google APIs, and AI-powered data processing.

AutoLoan is a full-featured loan origination and management platform designed to streamline the loan application process from submission to approval

This project implements a real-time video scene understanding system that combines YOLOv8 object detection, vision-language captioning, and LLM-based caption refinement to generate concise, factual, and context-aware descriptions of live video streams.

Automate and scale your LinkedIn job search process using a low-code automation pipeline built with n8n and the Bolt platform. This workflow scrapes jobs, evaluates relevance using AI, generates customized resumes, and logs structured job data for tracking and applications.

Sidekick is an intelligent multi-agent research assistant that combines the power of LangGraph and Gradio to deliver reliable, up-to-date answers. The system employs a unique worker-evaluator architecture where a tool-using worker agent performs tasks while an evaluator agent verifies outputs against user-defined success criteria.

An intelligent conversational interface that transforms natural language questions into secure, context-aware MySQL queries for market research analytics. Built with LangChain and Streamlit, this application provides a safe, read-only SQL execution environment with conversation memory and automated insights generation.

An intelligent document processing system that automatically classifies and analyzes financial documents using a hybrid approach of rule-based logic and LLM-powered analysis.

This project implements a Retrieval-Augmented Generation (RAG) system that combines real-time internet search with Large Language Model capabilities to provide accurate, context-aware answers to user queries.

An advanced AI-powered interview analysis system that combines speech recognition, natural language processing, and computer vision technologies to provide comprehensive candidate evaluation.

The YOLOv8n Stock Pattern Detection model is designed to adapt to the fast-paced nature of live trading environments. Its ability to operate on real-time video data allows traders and investors to harness pattern-based insights without delay.

Automated PCB defect detection system using Ultralytics YOLOv8. Features a robust XML-to-YOLO preprocessing pipeline to detect 6 defect types (e.g., Missing Hole, Short) with microscopic precision. Trained at 1024px resolution on the DeepPCB dataset and optimized for Google Colab (T4 GPU) with automated model persistence to Google Drive.

A comprehensive e-commerce web application built with PHP and MySQL, featuring a complete online shopping experience with advanced admin management capabilities.

About It is a multi-tenant SaaS platform built with Django REST framework that enables seamless data ingestion, validation, enrichment, and reporting, leveraging OpenAI API for advanced insights and ensuring data isolation and security.

TruthBot is an intelligent fact-checking system that leverages AI agents, web search, and multi-agent orchestration to verify claims and deliver clear, evidence-backed verdicts. Built with modern technologies, it combines powerful backend services with an intuitive frontend interface.

No description provided.