Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Docker image that provides a Minecraft Server for Java Edition that automatically installs/upgrades versions, modloaders, modpacks and more at startup

The open source coding agent.

An open collection of methodologies to help with successful training of large language models.

real time face swap and one-click video deepfake with only a single image

The fastest way to compute matrix profiles on CPU and GPU!

Modular CSS Library that brings the beauty of Terminal UIs to the browser

Text-based user interface CSS library

extract text from any document. no muss. no fuss.

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

Merlion: A Machine Learning Framework for Time Series Intelligence

An active fork of curl-impersonate with more versions and build targets. A series of patches that make curl requests look like Chrome, Firefox and Safari.

PyMC educational resources

WoeUSB-ng is a simple tool that enable you to create your own usb stick windows installer from an iso image or a real DVD. This is a rewrite of original WoeUSB.

Papers and online resources related to machine learning fairness

A collective list of free APIs

A lightweight fuzzy-search library, with zero dependencies

Following Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish

mactop - Apple Silicon Monitor Top

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

Ray tracing 25 scenes in 25 days with POV-Ray

A Python library for the Docker Engine API

strip output from Jupyter and IPython notebooks

MLX: An array framework for Apple silicon

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

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

A benchmark suite containing 1 million compilable programs, mined from the largest public C repositories on GitHub.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Typer, build great CLIs. Easy to code. Based on Python type hints.