#machine-learning

A unified interface for distributed computing. Fugue executes SQL, Python, Pandas, and Polars code on Spark, Dask and Ray without any rewrites.

End-to-end ML toolkit automating the complete workflow — data profiling, preprocessing, feature engineering, model selection, training, validation, explainability, drift monitoring, fairness checks, and interactive HTML reporting. Includes a full CLI for zero-code ML pipelines. Python 3.10+.

The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL — remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

HyPSTER - Configuration Framework for Optimizing AI & AI Systems

NMA Computational Neuroscience course

A new library for all of the newest ai algorithms

HTML page, form and field type classifier using ML (LogReg + CRF)

Graph Neural Networks in Julia

Bridge your scikit-learn scaler parameters between Python sessions and users. Distribute your scaling across multiple processes and data subsets.

[DEPRECATED] Moved to ROCm/rocm-libraries repo

MS²PIP: Fast and accurate peptide spectrum prediction for multiple fragmentation methods, instruments, and labeling techniques.

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

WildlifeDatasets: An open-source toolkit for animal re-identification

Shared Python utilities used across the TabPFN ecosystem — data helpers, regression result handling, cost estimation, and optional telemetry.

SciRS2 - Scientific Computing and AI in Rust., providing SciPy-compatible APIs while leveraging Rust's performance, safety, and concurrency features. Unlike traditional scientific libraries

Effector - a Python package for global and regional effect methods

The Ruby framework for programming—rather than prompting—language models.

A .NET Core REST client for the Constructor.io API

A high-performance automatic differentiation library for Rust

Python package for graph statistics

Matrix manipulation and computation library

A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.

Profile PyTorch models for FLOPs and parameters, helping to evaluate computational efficiency and memory usage.

A well tested and comprehensive Golang statistics library package with no dependencies.

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Hootenanny conflates multiple maps into a single seamless map.

A simple python implementation of Fuzzy C-means algorithm.

Universal LLM API client — 163 providers, 14 native language bindings, powered by a Rust core

Pre-trained Neural Network models in Axon (+ 🤗 Models integration)

Traditional machine learning on top of Nx