AI-powered Markdown note taking app - leverage vector embeddings and LLMs with your personal notes - 100% local or in the cloud

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper

A multi-agent reinforcement learning environment to design and benchmark control strategies aimed at reducing drag in turbulent open channel flow

Visually explore Python object graphs

A minimalist design exploration

Hunt down social media accounts by username across social networks

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

ALIEN is a CUDA-powered artificial life simulation program.

LLM101n: Let's build a Storyteller

Synchrosqueezing, wavelet transforms, and time-frequency analysis in Python

Retrying library for Python

OCR, layout analysis, reading order, table recognition in 90+ languages

The engine of the RenderCV App

Vizro is a toolkit for creating modular data visualization applications.

Machine Learning Engineering Open Book

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

Dara is a dynamic application framework designed for creating interactive web apps with ease, all in pure Python.

A collection of libraries to optimise AI model performances

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

VisualHFT is a cutting-edge GUI platform for market analysis, focusing on real-time visualization of market microstructure. Built with WPF & C#, it displays key metrics like Limit Order Book dynami…

Learn database internals by implementing it from scratch.

🕸️ Web apps in pure Python 🐍

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

A new markup-based typesetting system that is powerful and easy to learn.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

a programming library with geometric algorithms

Source code for Twitter's Recommendation Algorithm

A high-performance, zero-overhead, extensible Python compiler using LLVM

A playbook for systematically maximizing the performance of deep learning models.