Investigative data journalism: quantifying fixable waste in US healthcare, one issue at a time. Open-source analysis of CMS, OECD, and federal datasets. $98.6B in savings identified so far.

Hundreds of models & providers. One command to find what runs on your hardware.

AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML

A Grammar of Graphics for Python

Official implementation of "Continuous Autoregressive Language Models"

a simple decorator to cache the results of computationally heavy functions

SuperEasy 100% Local RAG with Ollama

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 91+ formats. Available for Rust, Pyt…

This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

A fast multimodal LLM for real-time voice

[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

The fastai book, published as Jupyter Notebooks

AirLLM 70B inference with single 4GB GPU

Refine high-quality datasets and visual AI models

Fast Desktop Switching Device

Mamba SSM architecture

Distribute and run LLMs with a single file.

Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).

📡 implementation of multi object tracking algorithms including PMBM (Poisson Multi Bernoulli Mixture filter) in Python 🐍

Recognize license plates (and numbers) using fine-tuned yolov8, OCR (tesseract) and Hikvision camera

PhyCV: The First Physics-inspired Computer Vision Library

A fast, secure, and portable multichain light client for Ethereum

MotionPlus has moved into Motion

Motion, a software motion detector. Home page: https://motion-project.github.io/

A GPU implementation of Convolutional Neural Nets in C++

Autonomous Racing Robot With an Arduino, a Raspberry Pi and a Pi Camera

Machine Learning for RC Cars