#deep-learning

An Engine-Agnostic Deep Learning Framework in Java

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Graph Neural Network Library for PyTorch

Relax! Flux is the ML library that doesn't make you tensor

Machine learning metrics for distributed, scalable PyTorch applications.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

BirdNET analyzer for scientific audio data processing.

optimizer & lr scheduler & loss function collections in PyTorch

A CLI for Kubeflow.

The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

A deep learning framework for multi-animal pose tracking.

X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, and multimodal data, combining versatile built-in tools with state-of-the-art AI models and flexible multi-format export.

High-performance automatic differentiation of LLVM and MLIR.

Easiest and laziest way for building multi-agent LLMs applications.

Next Generation Machine Learning, Statistics and Deep Learning in PURE Rust

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Optimized primitives for collective multi-GPU communication

Faster structured generation

The fastai deep learning library

Collection of eclectic utils for python.

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

SKaiNET makes local AI practical for developers: simple to build with, multiplatform by design, and optimized for native performance without compromises.

Open-source tabular foundation model for fast, training-free regression with predictive distributions.

A Living Benchmark for Machine Learning on Tabular Data

💫 Industrial-strength Natural Language Processing (NLP) in Python

Cross-platform, customizable ML solutions for live and streaming media.

JAX-based neural network library

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.