Will

ATS Buddy is a production-ready, serverless AI resume analyzer built on AWS Bedrock. It intelligently compares resumes against job descriptions, providing compatibility scores, missing keyword detection, and AI-powered resume enhancements—all while ensuring enterprise-grade PII protection and cost-efficient auto-scaling.

AI-powered outbound calling chatbot built with Twilio, FastAPI, and Pipecat, supporting real-time voice streaming and LLM integration.

A collection of 50 mini frontend projects built over 50 days to practice HTML, CSS, and JavaScript fundamentals through hands-on UI challenges.

A React application bootstrapped with Create React App, offering a modern development setup with hot reloading, built-in testing, and optimized production builds, making it an ideal starting point for building and scaling web applications quickly and efficiently.

A Next.js application bootstrapped with create-next-app, featuring file-based routing, built-in API routes, fast hot reloading, and optimized font loading, ready for local development and seamless deployment on Vercel.

A powerful AI assistant which can understand voice, image, access web process data. screenshot, clipboard, Keyboard shortcuts and can be extended with custom logic

AgentX is an experiment to develop autonomous agents so you can automate everything! This project is inspired by Auto-GPT, babyagi, SuperAGI, and other agents.

AI-powered FastAPI service that generates OpenAPI v3 specifications from natural language prompts

ChatGPT Recipe Studiois for creating and managing ChatGPT "recipes" - preset text processing patterns for rephrasing, summarizing, replying, and email creation. Built with Python & PyQt6, it offers a clean interface to save and reuse your most effective GPT prompts.Length: 214 characters

pg-diff is a PostgreSQL schema and data comparison tool that detects structural and data-level differences between databases, supporting use cases such as migration validation, regression checks, and cross-environment consistency audits.

Week View Component for react-native

This is a simple machine learning model which analyzes whether a credit card transaction is fraudlent or not. The dataset is downloaded from kaggle, check the readme for link to dataset.

Developing a machine learning model to detect and classify oral cancer levels from images. It involves data collection, preprocessing, feature extraction, selection, and model building using techniques like CNNs.

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).

LLM-powered pipeline for parsing .eml files, extracting HTML bodies, classifying email attachments as relevant or irrelevant based solely on HTML context, and evaluating results against ground truth using automated metrics.