Mohd Abuzar

*📚 YouTube Learning Assistant – NotebookLM Clone* Interactive AI Assistant to learn from YouTube videos using Gemini Pro LLM, FastAPI, and Streamlit. Chat with transcripts, ask questions, and listen to summaries. Fully Dockerized & deployment-ready.

🌟 RAG System with Gemini and LangChain A production-ready Retrieval-Augmented Generation (RAG) system powered by Google's Gemini model and LangChain, featuring document upload, semantic search, and AI-powered question answering. Key Features 🔍 Document Processing: PDF ingestion with text chunking 🧠 Vector Embeddings: Google's Gemini embedding

Struggling to decide what to cook? This recipe recommendation system provides personalized suggestions based on your dietary needs, available ingredients, and culinary preferences, making meal planning easier and more enjoyable.

The IPL Win Probability ML Model is a predictive analytics system designed to estimate the likelihood of a team winning a match during the Indian Premier League (IPL). The model leverages machine learning algorithms and historical IPL data to make accurate, real-time predictions during live matches or pre-match analysis.

🧑‍⚕️ Nadi Pulse Anemia Diabetes Prediction. A diabetes prediction project that use optical sensor data to predict patient Diabetes and Anemia.

predict plant disease using IP web cam.

OpenClaw Android Setup Guide Transform any old Android device into a 24/7 AI agent running locally. This guide provides step-by-step instructions for installing and running OpenClaw on Android using Termux and Ubuntu (proot), no PC or cloud server required. What You'll Get Fully local AI agent running on Android 10+ Web-based dashboard accessible

Run the real ubuntu on your android phone.

Run Claude Code + Ollama + VS Code On Phone For FREE

Run Hermes Agent - a self-evolving AI assistant - on any Android device using Termux. One-line installation.

OpenClaw with Ollama is a lightweight, high-performance integration designed to run sophisticated AI agents locally on Android devices. By leveraging the power of Termux and the flexibility of Ollama, this project enables a completely private, free, and offline-capable AI workstation in your pocket.

A simple guide to run Claude Code in Termux on Android using OpenRouter free models for AI-assisted coding directly from your phone.

No description.

Nanobot is a personal AI assistant inspired by OpenClaw. It delivers core agent functionality in just ~4,000 lines of code—99% smaller than alternatives, making it perfect for mobile devices.

No description.

Run uncensored AI on any system locally via USB drive.

VoidClaw is a universal autonomous AI command centre that runs seamlessly on Windows, Mac, Linux, and Android. It acts as a local-first digital assistant that manages your files, automates web tasks, and controls your devices with an evolutionary memory that adapts to your unique workflow.

Run Linux Desktop on any Android (No Root!)

A one-command shell script that installs a full XFCE4 Linux desktop with GPU acceleration on Android phones via Termux, no root required, including a browser, VS Code, and networking tools.

OpenClaw allows you to manage your phone via a Telegram bot using the power of local AI (Ollama). No root access is required, making it accessible for almost any modern Android device

PicoClaw is an ultra-lightweight, open-source AI agent framework designed to run on resource-constrained hardware (like $10 RISC-V boards or old Android phones).

Run Uncensored ai on any android phone

run openclaude for free on PC and Android phones

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline on Windows, macOS, or Linux. No installs, no internet, just plug and play.

No description.

Run leaked claude code on android phone using termux.

/This project is a smart video recorder that automatically detects events in real-time using YOLOv8 object detection. Instead of recording hours of empty footage, it continuously buffers live video from a webcam or IP camera and only saves short clips when something meaningful happens — like a person, car, dog, cat, or bicycle appearing in frame./

🚀 A Model Context Protocol (MCP) server that enables AI assistants to send emails via SMTP. Built with FastMCP and supports Gmail SMTP integration.

Crawl4AI - Production-ready web crawler with AI-powered content extraction, JavaScript rendering, and beautiful dashboard. Run with Docker in seconds.

No description.

added some tools.

No description.

No description.

A comprehensive collection of machine learning projects developed during my **CODEXINTERN** internship, showcasing practical implementation of classification and regression algorithms on classic datasets. This portfolio demonstrates my hands-on experience with real-world machine learning problems and solutions.

No description.

No description.

No description.

web-scraping

No description.

🗑️ Garbage Classification Using CNN This project is a deep learning-based web app that classifies garbage images into six categories using a Convolutional Neural Network (CNN). Built with TensorFlow and Streamlit, the model predicts the type of waste from an uploaded image, helping to promote efficient waste sorting and recycling.

No description.

No description.

No description.

this is my first MCP server

This project is a smart video recorder that automatically detects events in real-time using YOLOv8 object detection. Instead of recording hours of empty footage, it continuously buffers live video from a webcam or IP camera and only saves short clips when something meaningful happens — like a person, car, dog, cat, or bicycle appearing in frame.

developed the multiagent system with the help of crewAI.

This project is a Pinterest-style image feed powered by a deep learning model that automatically classifies images as Real or Fake in real time. The application is built using Streamlit for the frontend and TensorFlow/Keras for inference, enabling seamless integration of machine learning into an interactive web interface

Built a production-style AI moderation pipeline using Hugging Face vision models to automatically label uploaded images and short videos as real or AI-generated.

No description.

No description.

Production-ready AI chatbot Agent system with FastAPI API layer, LangChain agent orchestration, Ollama model integration, and a mobile-ready Flet UI.

No description.

No description.

No description.

No description.

No description.

predict plant disease by plant's photo.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

Analyze your WhatsApp Chat in Seconds. Instant Insights: Discover who's texting the most messages, see peak activity times, and uncover hidden patterns.

predict disease using patient age and optical sensor's collected data of patient.

Predict the next words in your sentence. However, the model is trained on a very small dataset (Twitter dataset), so it may make mistakes.

This WhatsApp chat analyzer describe all your chats.

Object detection using transfer learning.

The Movies Recommender System ML Model is an advanced recommendation engine designed to personalize movie suggestions for users. Using machine learning algorithms, it analyzes user preferences, viewing history, and movie attributes to deliver tailored recommendations, enhancing user engagement and satisfaction.

This spam filter model can filter the spam and not spam message and mails . it is deploy on render

Message Statistics: View total messages, daily activity, and peak interaction times. Participant Insights: Analyze individual contributions, most active users, and reply patterns. Word Analysis: Discover frequently used words and emojis. Visualization: Generate charts and graphs to illustrate chat trends.

This detector can detect lung cancer with provided information. but this prediction only predict by given information. if you have serious problem please visit doctor .

No description.