Stars
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
This project contains a simple RAG Application created using TypeScript.
An interactive Formula 1 race visualisation and data analysis tool built with Python! 🏎️
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
This repository contains the Hugging Face Agents Course.
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
You like pytorch? You like micrograd? You love tinygrad! ❤️
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
A lightweight library for portable low-level GPU computation using WebGPU.
A Direct-to-Driver open mobility platform powering the next-generation of mobility applications in India.
This is a repo with links to everything you'd ever want to learn about data engineering
Streamlit — A faster way to build and share data apps.
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Focus on what matters instead of fighting with Git.
A light-weight, power efficient, and general purpose convolutional neural network
This repository contains the source code of our work on designing efficient CNNs for computer vision
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet
Lightweight justice for your single-board computer!
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
FastAPI framework, high performance, easy to learn, fast to code, ready for production
The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detection on Point Clouds"
Image augmentation for machine learning experiments.
Pyspark based Feature engineering package to generate entropy, dynamic lookback, risk and other statistical features
Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.