GPT-4 Vision Chrome Extension

AI Agent capable of automating various tasks using MCP

An AI powered PlantUML Editor App for iPad

Python code for openai live video narrator.

A lightweight Vision-Language-Action (VLA) baseline for MetaWorld robot-arm tasks using a pretrained CLIP-ViT vision transformer(openai/clip-vit-base-patch32), a small text transformer, and robot-state fusion

Generate DDLs from ER Diagrams using OpenAI Vision

This Python script processes a video file, generates a compelling description, creates a voiceover script in the style of David Attenborough, and synthesizes the voiceover using OpenAI's Text-to-Speech API.

🤖 🌐 Personal AI assistant that browses the web independently

The AI Expense Tracker is an expense management tool designed to simplify the process of tracking expenses by automating the extraction of necessary data from receipt images.

Generate K6 test case from a web page screenshot

VS Code extension for AI-assisted UX analysis, combining screenshot inspection, multi-agent evaluation, and an interactive webview.

Web-based AI image recognition app.

Multimodal Video Reasoning and Frame Analysis Platform for real-time intelligent monitoring.

An intelligent document navigation system that extracts topics, maps relationships, detects anomalies, and creates visual navigation tools for complex documents using LangGraph and OpenAI.

Smart Screen Reader- A Screen reader chrome extension for visually-impaired people. This is a Chrome extension that enhances web accessibility by: Generating image descriptions using AI, Summarizing entire pages, Allowing users to ask questions and automatically scroll to the relevant sections.

Enterprise vision-query Technical Architecture focusing on Scalability and High Performance.

AI-powered cross-browser UI/UX testing tool that captures screenshots across devices and uses OpenAI vision models to analyze layout, responsiveness, and compatibility issues.

Supercharge Legacy models with RAG, image analysis (GPT-4o vision), code execution, and web search. Transform it into a lean, multimodal powerhouse—smarter, faster, and more versatile, without the heavyweight cost.