Machine-learning-frameworks

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

The fastest path to AI-powered full stack observability, even for lean teams.

scikit-learn: machine learning in Python

Ecommerce Search and Discovery - marqo.ai

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

A hyperparameter optimization framework

Personal photo management powered by Go and Google TensorFlow. Browse, organize, and share your personal photo collection, using the latest technologies to automatically tag and find pictures.

Production-grade Rust-native trading engine with deterministic event-driven architecture

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

Open standard for machine learning interoperability

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Open Machine Learning Compiler Framework

Streamlit — A faster way to build and share data apps.

An Open Source Machine Learning Framework for Everyone

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

HeavyDB (formerly MapD/OmniSciDB)

The Julia Programming Language

Machine Learning Toolkit for Kubernetes

ModelScope: bring the notion of Model-as-a-Service to life.

Deep Learning for humans

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

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Visualizer for neural network and machine learning models.

🧙 Build, run, and manage data pipelines for integrating and transforming data.

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.

A game theoretic approach to explain the output of any machine learning model.

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

A Deep Learning Python Toolkit for Healthcare Applications.

Lightning ⚡️ fast forecasting with statistical and econometric models.

Curated list of Python resources for data science.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

Production-Grade ML System for Automated Unit of Measure Error Detection | 88-92% Accuracy | 94% Autonomy | KNIME Workflow

Long list of geospatial tools and resources

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

中国的Quant相关资源索引

Deepnote is a drop-in replacement for Jupyter with an AI-first design, sleek UI, new blocks, and native data integrations. Use Python, R, and SQL locally in your favorite IDE, then scale to Deepnote cloud for real-time collaboration, Deepnote agent, and deployable data apps. https://deepnote.com/

Implementation of papers in 100 lines of code.

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

High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.

Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.

🔐 AI decoding Trump's posts × stock market | AI 解碼川普推文 × 美股 | AIでトランプ投稿×株式市場を解読 — 31.5M models, 61.3% hit rate, open source

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

Open source AML and Fraud Detection using Machine Learning for Real-Time Transaction Monitoring

GeoAI: Artificial Intelligence for Geospatial Data

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python

Slips, a free software behavioral Python intrusion prevention system (IDS/IPS) that uses machine learning to detect malicious behaviors in the network traffic. Stratosphere Laboratory, AIC, FEL, CVUT in Prague.

Deepfakes Software For All

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Graph Neural Network Library for PyTorch

100-Days-Of-ML-Code中文版

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Fast and accurate AI powered file content types detection

AI Toolkit for Healthcare Imaging

MICCAI 2019-2026 Open Source Papers

🎓Automatically Update CV Papers Daily using Github Actions

DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.

WebApps in pure Python. No JavaScript, HTML and CSS needed

This repo contains annotated research papers that I found really good and useful

Single-cell analysis in Python. Scales to >100M cells.

NFStream: a Flexible Network Data Analysis Framework.

Python Client for Supabase. Query Postgres from Flask, Django, FastAPI. Python user authentication, security policies, edge functions, file storage, and realtime data streaming. Good first issue.

NLTK Source

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

Measure and optimize the energy consumption of your AI applications!

🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs

Google Research

:memo: An awesome Data Science repository to learn and apply for real world problems.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

An open-source, tool-augmented conversational language model from Fudan University

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

Automated Machine Learning pipelines. Builds the Open Short Term Energy Forecasting package.

NSFW detection on the client-side via TensorFlow.js

🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.

The fastai deep learning library

🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.

LakeSoul is an end-to-end, realtime cloud-native Lakehouse framework for fast data ingestion, concurrent updates, incremental analytics, multimodal data processing and vector search — powering next-generation BI and AI workloads.

The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial networks to create synthetic high-resolution wind and solar spatiotemporal data from coarse low-resolution inputs.

A toolkit for building AI-automated trading strategies on Kalshi prediction markets.

A low code Machine Learning personalized ranking service for articles, listings, search results, recommendations that boosts user engagement. A friendly Learn-to-Rank engine

Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.

:book: A curated list of resources dedicated to Natural Language Processing (NLP)

The free and privacy-friendly screen recorder with no limits 🎥

Fit interpretable models. Explain blackbox machine learning.

SFML is the first fully local AI solar forecast for Home Assistant, powered by a local Attention Transformer. No external AI — such as ChatGPT, Gemini, or Grok — required. Runs entirely on your device for complete privacy.

The intelligent & developer-friendly EMS to support real-time energy flexibility apps, rapidly and scalable.

Go implementation of the MediaDevices API.

A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

A Rust machine learning framework.

Next generation of automated data exploratory analysis and visualization platform.

A fork of gym-retro with additional games, emulators and supported platforms

Instant Kubernetes-Native Application Observability

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library 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.

Uniform Manifold Approximation and Projection

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Java dataframe and visualization library

Stable Diffusion web UI

Faster Whisper transcription with CTranslate2

Topic Modelling for Humans

🌊 Online machine learning in Python

Python Streaming DataFrames for Kafka

A lightweight header-only library for using Keras (TensorFlow) models in C++.

Collecting research materials on energy/entropy based models

Open-source ML platform for detecting deforestation, ice melt, and flooding from Sentinel-2 / Landsat imagery.

Open Machine Learning

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

Open source annotation tool for machine learning practitioners.

Deep learning framework for MRI reconstruction

Research Software for Neural Weather Prediction for Limited Area Modeling

TVM Documentation in Chinese Simplified / TVM 中文文档

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

Alluxio, data orchestration for analytics and machine learning in the cloud

SeisBench - A toolbox for machine learning in seismology

Best Practices on Recommendation Systems

Open Data Platform for analysts, quants and AI agents.

Making large AI models cheaper, faster and more accessible

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.

Slides, paper notes, class notes, blog posts, and research on ML 📉, statistics 📊, and AI 🤖.

mlpack: a fast, header-only C++ machine learning library

Research on Tabular Deep Learning: Papers & Packages

Gin provides a lightweight configuration framework for Python

Open3D: A Modern Library for 3D Data Processing

OWASP CycloneDX is a full-stack Bill of Materials (BOM) standard that provides advanced supply chain capabilities for cyber risk reduction. SBOM, SaaSBOM, HBOM, AI/ML-BOM, CBOM, OBOM, MBOM, VDR, and VEX

Collection of various algorithms implemented in R.

[IEEE TMI Best Paper Award] Official Implementation for UNet++

🧪Yet Another ICU Benchmark: a holistic framework for the standardization of clinical prediction model experiments. Provide custom datasets, cohorts, prediction tasks, endpoints, preprocessing, and models. Paper: https://arxiv.org/abs/2306.05109

Automated Quality Control and visual reports for Quality Assessment of structural (T1w, T2w) and functional MRI of the brain

Alpha Forge — an agentic AI operating system for systematic trading.

NOVA is a tool for annotating and analyzing behaviours in social interactions. It supports Annotators using Machine Learning already during the coding process. Further it features both, discrete labels and continuous scores and a visuzalization of streams recorded with the SSI Framework.

Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

Roadmap to becoming an Artificial Intelligence Expert in 2022

Data Science Roadmap from A to Z

A unified framework for privacy-preserving data analysis and machine learning

README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations.

A WebGL accelerated JavaScript library for training and deploying ML models.

阿布量化交易系统(股票，期权，期货，比特币，机器学习) 基于python的开源量化交易，量化投资架构

.NET for Apache® Spark™ makes Apache Spark™ easily accessible to .NET developers.

Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Probabilistic reasoning and statistical analysis in TensorFlow

✨ AI/ML Research

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.

The Modular Platform (includes MAX & Mojo)

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

邱锡鹏《神经网络与深度学习》第二版与通识版：电子书、章节目录、学习资源与勘误。

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

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

A flexible, adaptive classification system for dynamic text classification

Non-Intrusive Load Monitoring (NILM) for Home Assistant. Estimate appliance activity and energy usage from a whole-home power sensor, all locally.

Graph-based weather forecasting models. Originally, PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)

The world's simplest facial recognition api for Python and the command line

Deezer source separation library including pretrained models.

⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.

🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained

CapyMOA does efficient machine learning for data streams in Python. CapyMOA is a toolbox of methods and evaluators for: classification, regression, clustering, anomaly detection, semi-supervised learning, online continual learning, and drift detection for data streams.

MONAI Label is an intelligent open source image labeling and learning tool.

Self-healing edge computing agent with predictive failure detection and partition-resilient orchestration for Kubernetes

Visualize and compare datasets, target values and associations, with one line of code.

Shared repository for open-sourced projects from the Google AI Language team.

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.

A curated list of awesome responsible machine learning resources.

Supply chain security for ML

AI tutor powered by Theory-of-Mind reasoning

📄 🤖 AI for medical and scientific papers

Using Diffusion Models to Segment/Reconstruct Organs from Medical Images [AAAI Most influential Paper]

Alaska Project Ideas, mentored by the researchers and collaborators of University of Alaska and supported by open-source entities and enthusiasts in Alaska.

TensorFlow documentation

Probably the best curated list of data science software in Python.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

State-of-the-art 2D and 3D Face Analysis Project

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

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

🔥Highlighting the top ML papers every week.

Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.

Pythonic tool for orchestrating machine-learning/high performance/quantum-computing workflows in heterogeneous compute environments.

All the handwritten notes 📝 and source code files 🖥️ used in my YouTube Videos on Machine Learning & Simulation (https://www.youtube.com/channel/UCh0P7KwJhuQ4vrzc3IRuw4Q)

A lightweight adapter bridges SAM with medical imaging [MedIA]

TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.

Neural networks toolbox focused on medical image analysis

Open Neural Network Exchange to C compiler.

The official repository for the EuroCrops dataset.

A Static Analyzer for Java Powered by Machine Learning: Identifies Anti-Patterns Begging for Refactoring