Ayush Shekhar

AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private.

A Python app that records your screen and uses a local AI model to describe what you were doing, then lets you search or chat with your full screen history entirely on your own computer.

No description.

No description.

A multipage simple android login application that encompasses firebase facilities for different authentication options and multilanguage support

An E-learning platform using cloud computation

Project Made during Virtual Summer Internship under leadingindia.ai and BENNETT UNIVERSITY.

No description.

structured outputs for llms

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

LlamaIndex is the leading document agent and OCR platform

Production-ready platform for agentic workflow development.

Build, run, manage agentic software at scale.

A programming framework for agentic AI

No description.

No description.

An experimental open-source attempt to make GPT-4 fully autonomous.

No description.

No description.

No description.

LLM training in simple, raw C/CUDA

A simple linear regression model trained on a given dataset that predicts house pricing

Face Identification is a Python-based project designed for Raspberry Pi, utilizing OpenCV libraries for accurate face recognition.

The Compressive Strength Predictor is an android application that utilizes ML model trained on dataset and an Flask API deployed on AWS EC2 instance to estimate the compressive strength of a material based on four input parameters: Grade, UPV (Ultrasonic Pulse Velocity), Rebound, and Age

This repository contains implementations of various classification and clustering algorithms applied to diverse datasets for classification and prediction tasks. The algorithms employed include K-means clustering, Simple Linear Regression, Principal Component Analysis (PCA), Support Vector Machine (SVM), and Naive Bayes.

Cloud based student attendance system

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Qemu kernel for emulating Rpi on QEMU

This is a Computer vision package that makes its easy to run Image processing and AI functions. At the core it uses OpenCV and Mediapipe libraries.

Samples for Hyperledger Fabric

The official GitHub mirror of the Chromium source

PyTorch package for the discrete VAE used for DALL·E.

Kubernetes website and documentation repo: