Machine Learning Frameworks

TensorFlow - Google’s open-source platform for machine learning. GitHub Repo PyTorch - An open-source machine learning library developed by Facebook. GitHub Repo Keras - High-level neural networks API, capable of running on top of TensorFlow, CNTK, or Theano. GitHub Repo scikit-learn - Machine learning library for Python, offering simple and efficient tools for data mining and data analysis. GitHub Repo MXNet - A deep learning framework used by Amazon. GitHub Repo Caffe - A deep learning framework made with expression, speed, and modularity in mind. GitHub Repo Theano - A Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. GitHub Repo CNTK (Microsoft Cognitive Toolkit) - Microsoft’s open-source toolkit for deep learning. GitHub Repo Chainer - A flexible framework of neural networks that supports dynamic computational graphs. GitHub Repo PaddlePaddle - An open-source deep learning platform by Baidu. GitHub Repo FastAI - A library that provides practitioners with high-level components for building deep learning models. GitHub Repo MLlib - Spark’s scalable machine learning library. GitHub Repo H2O - An open-source, in-memory, distributed, fast, and scalable machine learning and predictive analytics platform. GitHub Repo DL4J (Deeplearning4j) - A deep learning library written for Java and the JVM. GitHub Repo TensorFlow Lite - For on-device inference with deep learning models. GitHub Repo ONNX (Open Neural Network Exchange) - An open format to represent deep learning models. GitHub Repo TensorFlow.js - A library for machine learning in JavaScript. GitHub Repo PySyft - A library for encrypted, privacy-preserving deep learning. GitHub Repo Gluon - A high-level API for MXNet. GitHub Repo Caffe2 - A lightweight, modular, and scalable deep learning framework (merged with PyTorch). GitHub Repo

Natural Language Processing (NLP)

NLTK (Natural Language Toolkit) - A suite of libraries and programs for symbolic and statistical natural language processing. GitHub Repo spaCy - Industrial-strength natural language processing in Python. GitHub Repo Gensim - A library for topic modelling, document indexing, and similarity retrieval with large corpora. GitHub Repo Stanford CoreNLP - A Java suite of core NLP tools. GitHub Repo OpenNLP - An open-source library for maximum entropy tagging and named entity extraction. GitHub Repo Hugging Face Transformers - State-of-the-art Natural Language Processing for TensorFlow, PyTorch, and JAX. GitHub Repo Flair - A powerful NLP library for Python. GitHub Repo fastText - Library for efficient learning of word representations and sentence classification. GitHub Repo Polyglot - A natural language pipeline that supports massive multilingual applications. GitHub Repo TextBlob - A library for processing textual data. It provides a simple API for diving into common natural language processing tasks. GitHub Repo Pattern - A web mining module for Python, with tools for web services, data mining, NLP, machine learning, and network analysis. GitHub Repo MITIE - A library for named entity recognition, and other information extraction tasks. GitHub Repo OpenNMT - An open-source toolkit for neural machine translation (NMT). GitHub Repo AllenNLP - An open-source research library for building deep learning models for NLP. GitHub Repo NLP Architect - Intel’s NLP library for exploring the state-of-the-art deep learning topologies and techniques. GitHub Repo Stanford Parser - A program for parsing natural language sentences into their grammatical structure. GitHub Repo Senpy - A framework for sentiment analysis and emotion detection. GitHub Repo DeepPavlov - An open-source library for natural language processing and deep learning. GitHub Repo LASER (Language-Agnostic SEntence Representations) - For multilingual sentence embeddings. GitHub Repo BERT - Google’s Bidirectional Encoder Representations from Transformers. GitHub Repo

Computer Vision

OpenCV - A library of programming functions mainly aimed at real-time computer vision. GitHub Repo Dlib - A modern C++ toolkit containing machine learning algorithmsOops, something broke. GitHub Repo TensorFlow Object Detection API - A framework for object detection that uses TensorFlow. GitHub Repo Detectron2 - Facebook AI Research’s next generation software system that implements state-of-the-art object detection algorithms. GitHub Repo MMDetection - An open-source object detection toolbox based on PyTorch. GitHub Repo YOLO (You Only Look Once) - Real-time object detection system known for its speed and accuracy. GitHub Repo SSD (Single Shot MultiBox Detector) - A method for detecting objects in images using a single deep neural network. GitHub Repo Mask R-CNN - Extends Faster R-CNN by adding instance segmentation. GitHub Repo FACETS - Google’s visualization tool for understanding machine learning datasets and models, with a focus on image data. GitHub Repo Kornia - A differentiable computer vision library for PyTorch, focusing on geometric computer vision. GitHub Repo Albumentations - Fast and flexible image augmentation library in Python for deep learning. GitHub Repo imgaug - Image augmentation for machine learning experiments in Python. GitHub Repo OpenFace - A Python and Torch implementation of face recognition with deep neural networks. GitHub Repo Face_recognition - The world’s simplest facial recognition api for Python. GitHub Repo SimpleCV - A framework for building computer vision applications. GitHub Repo

Data Analysis and Preprocessing

Pandas - A powerful data analysis toolkit for Python. GitHub Repo NumPy - Fundamental package for scientific computing with Python. GitHub Repo Dask - Scalable analytics in Python, designed to scale up operations on larger-than-memory datasets. GitHub Repo Apache Arrow - A columnar memory format for flat and hierarchical data, organized for efficient analytic operations. GitHub Repo OpenML - A platform for sharing and obtaining machine learning datasets, algorithms, and experiments. GitHub Repo Featuretools - A framework to perform automated feature engineering. GitHub Repo Imbalanced-learn - A Python package offering a number of re-sampling techniques commonly used in datasets showing strong between-class imbalance. GitHub Repo Statsmodels - A Python module that allows users to explore data, estimate statistical models, and perform statistical tests. GitHub Repo Vaex - A high performance out-of-core DataFrames for Python, ML, visualization, and big data. GitHub Repo PyMC3 - Probabilistic Programming in Python: Bayesian Modeling and Probabilistic Machine Learning with Theano. GitHub Repo PyCaret - An open-source, low-code machine learning library in Python that automates machine learning workflows. GitHub Repo

Reinforcement Learning

Gym - A toolkit for developing and comparing reinforcement learning algorithms. GitHub Repo TensorFlow Agents - A library for reinforcement learning in TensorFlow. GitHub Repo RLlib - An open-source library for reinforcement learning that offers both high scalability and a unified API. GitHub Repo Stable Baselines - A set of improved implementations of reinforcement learning algorithms based on OpenAI Baselines. GitHub Repo Keras-RL - Deep Reinforcement Learning for Keras. GitHub Repo Dopamine - A research framework for fast prototyping of reinforcement learning algorithms. GitHub Repo Ray - A high-performance distributed execution framework that includes RLlib for reinforcement learning. GitHub Repo Coach - An open-source library for training deep reinforcement learning agents. GitHub Repo Horizon - A platform for applied reinforcement learning by Facebook AI Research. GitHub Repo

Time Series Analysis

Prophet - A procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. GitHub Repo StatsForecast - A fast and parallel time series forecasting library for Python. GitHub Repo Pykalman - A Python library for Kalman filters and other related optimal estimation methods. GitHub Repo Darts - A Python library for easy manipulation and forecasting of time series. GitHub Repo GluonTS - A Python toolkit for probabilistic time series modeling, based on the Gluon API. GitHub Repo

Others

TensorBoard - TensorFlow’s visualization toolkit. GitHub Repo MLflow - A platform to manage the end-to-end machine learning lifecycle, including experimentation, reproducibility, and deployment. GitHub Repo Seldon Core - An MLOps framework to package, deploy, scale, and monitor machine learning models on Kubernetes. GitHub Repo Kubeflow - The machine learning toolkit for Kubernetes. GitHub Repo Jupyter Notebook - An open-source web application that allows you to create and share documents containing live code, equations, visualizations, and narrative text. GitHub Repo JupyterLab - The next-generation user interface for Project Jupyter, offering a flexible and powerful notebook environment. GitHub Repo Papermill - A tool for parameterizing and executing Jupyter Notebooks. GitHub Repo SHAP (SHapley Additive exPlanations) - A game theoretic approach to explain the output of any machine learning model. GitHub Repo LIME (Local Interpretable Model-agnostic Explanations) - A library for debugging/inspecting machine learning models and explaining their predictions. GitHub Repo ELI5 (Explain Like I’m 5) - A library for debugging/inspecting machine learning models and explaining their predictions. GitHub Repo Fairlearn - A Python library for assessing and improving fairness in machine learning models. GitHub Repo AI Fairness 360 (AIF360) - An open-source toolkit to examine, report, and mitigate bias in machine learning datasets and models. GitHub Repo TensorFlow Data Validation (TFDV) - A library for exploring and validating machine learning data. GitHub Repo TensorFlow Transform (TFT) - A library for preprocessing data with TensorFlow. GitHub Repo TensorFlow Model Analysis (TFMA) - A library for evaluating TensorFlow models. GitHub Repo TensorFlow Serving - A flexible, high-performance serving system for machine learning models, designed for production environments. GitHub Repo TensorFlow Extended (TFX) - An end-to-end platform for deploying production ML pipelines. GitHub Repo MLKit - A mobile SDK by Google that brings Google’s machine learning expertise to Android and iOS apps. GitHub Repo Ludwig - A deep learning toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code. GitHub Repo ONNX Runtime - A cross-platform inference and training machine-learning accelerator by Microsoft, compatible with models from many frameworks including PyTorch, TensorFlow, and more. GitHub Repo

AI Agents and Multi-Agent Systems

AutoGen - A framework by Microsoft for creating and managing multi-agent conversations, enabling the development of complex AI systems that can collaborate to achieve specific goals. GitHub Repo LangChain - An open-source framework designed to simplify the creation of applications that utilize language models, particularly for building agents that can interact with tools and APIs. GitHub Repo CrewAI - A framework that allows developers to create crews of AI agents, each with specific roles, to work collaboratively on tasks, enhancing productivity through delegation and teamwork. GitHub Repo AgentGPT - An experimental open-source project that allows users to create autonomous AI agents capable of completing tasks by breaking them down into subtasks and executing them. GitHub Repo BabyAGI - A Python-based task management system that uses AI to create, prioritize, and execute tasks autonomously, inspired by the concept of AGI but focused on baby steps towards it. GitHub Repo Jarvis - An open-source project for creating personal AI assistants that can understand commands, manage tasks, and interact with various systems, inspired by the AI from Iron Man. GitHub Repo

New AI Tools and Frameworks

Hugging Face Diffusers - A library for state-of-the-art diffusion models, which are used for generating high-quality images from textual descriptions, part of the broader trend towards generative AI. GitHub Repo Open Interpreter - A tool that allows the execution of code based on natural language instructions, bridging the gap between human language and programming, particularly useful for AI agents. GitHub Repo Vanna.AI - An open-source tool for creating AI-powered data products, focusing on simplifying the process of turning data into insights with AI assistance. GitHub Repo PR-Agent - An AI tool designed to assist in the pull request process by providing automated code reviews, suggestions, and even fixing minor issues, enhancing developer productivity. GitHub Repo Aide - An AI assistant for developers that helps with code understanding, generation, and debugging by integrating with IDEs, improving coding efficiency. GitHub Repo Mitra - An open-source project for conversational AI, focusing on creating chatbots that can understand and respond in multiple languages and dialects. GitHub Repo TensorFlow - Google’s open-source platform for machine learning. GitHub Repo PyTorch - An open-source machine learning library developed by Facebook. GitHub Repo Keras - High-level neural networks API, capable of running on top of TensorFlow, CNTK, or Theano. GitHub Repo scikit-learn - Machine learning library for Python, offering simple and efficient tools for data mining and data analysis. GitHub Repo MXNet - A deep learning framework used by Amazon. GitHub Repo Caffe - A deep learning framework made with expression, speed, and modularity in mind. GitHub Repo Theano - A Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. GitHub Repo CNTK (Microsoft Cognitive Toolkit) - Microsoft’s open-source toolkit for deep learning. GitHub Repo Chainer - A flexible framework of neural networks that supports dynamic computational graphs. GitHub Repo PaddlePaddle - An open-source deep learning platform by Baidu. GitHub Repo FastAI - A library that provides practitioners with high-level components for building deep learning models. GitHub Repo MLlib - Spark’s scalable machine learning library. GitHub Repo H2O - An open-source, in-memory, distributed, fast, and scalable machine learning and predictive analytics platform. GitHub Repo DL4J (Deeplearning4j) - A deep learning library written for Java and the JVM. GitHub Repo TensorFlow Lite - For on-device inference with deep learning models. GitHub Repo ONNX (Open Neural Network Exchange) - An open format to represent deep learning models. GitHub Repo TensorFlow.js - A library for machine learning in JavaScript. GitHub Repo PySyft - A library for encrypted, privacy-preserving deep learning. GitHub Repo Gluon - A high-level API for MXNet. GitHub Repo Caffe2 - A lightweight, modular, and scalable deep learning framework (merged with PyTorch). GitHub Repo

Natural Language Processing (NLP)

NLTK (Natural Language Toolkit) - A suite of libraries and programs for symbolic and statistical natural language processing. GitHub Repo spaCy - Industrial-strength natural language processing in Python. GitHub Repo Gensim - A library for topic modelling, document indexing, and similarity retrieval with large corpora. GitHub Repo Stanford CoreNLP - A Java suite of core NLP tools. GitHub Repo OpenNLP - An open-source library for maximum entropy tagging and named entity extraction. GitHub Repo Hugging Face Transformers - State-of-the-art Natural Language Processing for TensorFlow, PyTorch, and JAX. GitHub Repo Flair - A powerful NLP library for Python. GitHub Repo fastText - Library for efficient learning of word representations and sentence classification. GitHub Repo Polyglot - A natural language pipeline that supports massive multilingual applications. GitHub Repo TextBlob - A library for processing textual data. It provides a simple API for diving into common natural language processing tasks. GitHub Repo Pattern - A web mining module for Python, with tools for web services, data mining, NLP, machine learning, and network analysis. GitHub Repo MITIE - A library for named entity recognition, and other information extraction tasks. GitHub Repo OpenNMT - An open-source toolkit for neural machine translation (NMT). GitHub Repo AllenNLP - An open-source research library for building deep learning models for NLP. GitHub Repo NLP Architect - Intel’s NLP library for exploring the state-of-the-art deep learning topologies and techniques. [GitHub Repo](https://github.com/NLP- Architect/NLP-Architect) Stanford Parser - A program for parsing natural language sentences into their grammatical structure. GitHub Repo Senpy - A framework for sentiment analysis and emotion detection. GitHub Repo DeepPavlov - An open-source library for natural language processing and deep learning. GitHub Repo LASER (Language-Agnostic SEntence Representations) - For multilingual sentence embeddings. GitHub Repo BERT - Google’s Bidirectional Encoder Representations from Transformers. GitHub Repo

Computer Vision

OpenCV - A library of programming functions mainly aimed at real-time computer vision. GitHub Repo Dlib - A modern C++ toolkit containing machine learning algorithmsOops, something broke. GitHub Repo TensorFlow Object Detection API - A framework for object detection that uses TensorFlow. GitHub Repo Detectron2 - Facebook AI Research’s next generation software system that implements state-of-the-art object detection algorithms. GitHub Repo MMDetection - An open-source object detection toolbox based on PyTorch. GitHub Repo YOLO (You Only Look Once) - Real-time object detection system known for its speed and accuracy. GitHub Repo SSD (Single Shot MultiBox Detector) - A method for detecting objects in images using a single deep neural network. GitHub Repo Mask R-CNN - Extends Faster R-CNN by adding instance segmentation. GitHub Repo FACETS - Google’s visualization tool for understanding machine learning datasets and models, with a focus on image data. GitHub Repo Kornia - A differentiable computer vision library for PyTorch, focusing on geometric computer vision. GitHub Repo Albumentations - Fast and flexible image augmentation library in Python for deep learning. GitHub Repo imgaug - Image augmentation for machine learning experiments in Python. GitHub Repo OpenFace - A Python and Torch implementation of face recognition with deep neural networks. GitHub Repo Face_recognition - The world’s simplest facial recognition api for Python. GitHub Repo SimpleCV - A framework for building computer vision applications. GitHub Repo Data Analysis and Preprocessing

Pandas - A powerful data analysis toolkit for Python. GitHub Repo NumPy - Fundamental package for scientific computing with Python. GitHub Repo Dask - Scalable analytics in Python, designed to scale up operations on larger-than-memory datasets. GitHub Repo Apache Arrow - A columnar memory format for flat and hierarchical data, organized for efficient analytic operations. GitHub Repo OpenML - A platform for sharing and obtaining machine learning datasets, algorithms, and experiments. GitHub Repo Featuretools - A framework to perform automated feature engineering. GitHub Repo Imbalanced-learn - A Python package offering a number of re-sampling techniques commonly used in datasets showing strong between-class imbalance. GitHub Repo Statsmodels - A Python module that allows users to explore data, estimate statistical models, and perform statistical tests. GitHub Repo Vaex - A high performance out-of-core DataFrames for Python, ML, visualization, and big data. GitHub Repo PyMC3 - Probabilistic Programming in Python: Bayesian Modeling and Probabilistic Machine Learning with Theano. GitHub Repo PyCaret - An open-source, low-code machine learning library in Python that automates machine learning workflows. GitHub Repo

Reinforcement Learning

Gym - A toolkit for developing and comparing reinforcement learning algorithms. GitHub Repo TensorFlow Agents - A library for reinforcement learning in TensorFlow. GitHub Repo RLlib - An open-source library for reinforcement learning that offers both high scalability and a unified API. GitHub Repo Stable Baselines - A set of improved implementations of reinforcement learning algorithms based on OpenAI Baselines. GitHub Repo Keras-RL - Deep Reinforcement Learning for Keras. GitHub Repo Dopamine - A research framework for fast prototyping of reinforcement learning algorithms. GitHub Repo Ray - A high-performance distributed execution framework that includes RLlib for reinforcement learning. GitHub Repo Coach - An open-source library for training deep reinforcement learning agents. GitHub Repo Horizon - A platform for applied reinforcement learning by Facebook AI Research. GitHub Repo

Time Series Analysis

Prophet - A procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. GitHub Repo StatsForecast - A fast and parallel time series forecasting library for Python. GitHub Repo Pykalman - A Python library for Kalman filters and other related optimal estimation methods. GitHub Repo Darts - A Python library for easy manipulation and forecasting of time series. GitHub Repo GluonTS - A Python toolkit for probabilistic time series modeling, based on the Gluon API. GitHub Repo

TensorBoard - TensorFlow’s visualization toolkit. GitHub Repo MLflow - A platform to manage the end-to-end machine learning lifecycle, including experimentation, reproducibility, and deployment. GitHub Repo Seldon Core - An MLOps framework to package, deploy, scale, and monitor machine learning models on Kubernetes. GitHub Repo Kubeflow - The machine learning toolkit for Kubernetes. GitHub Repo Jupyter Notebook - An open-source web application that allows you to create and share documents containing live code, equations, visualizations, and narrative text. GitHub Repo JupyterLab - The next-generation user interface for Project Jupyter, offering a flexible and powerful notebook environment. GitHub Repo Papermill - A tool for parameterizing and executing Jupyter Notebooks. GitHub Repo SHAP (SHapley Additive exPlanations) - A game theoretic approach to explain the output of any machine learning model. GitHub Repo LIME (Local Interpretable Model-agnostic Explanations) - A library for debugging/inspecting machine learning models and explaining their predictions. GitHub Repo ELI5 (Explain Like I’m 5) - A library for debugging/inspecting machine learning models and explaining their predictions. GitHub Repo Fairlearn - A Python library for assessing and improving fairness in machine learning models. GitHub Repo AI Fairness 360 (AIF360) - An open-source toolkit to examine, report, and mitigate bias in machine learning datasets and models. GitHub Repo TensorFlow Data Validation (TFDV) - A library for exploring and validating machine learning data. GitHub Repo TensorFlow Transform (TFT) - A library for preprocessing data with TensorFlow. GitHub Repo TensorFlow Model Analysis (TFMA) - A library for evaluating TensorFlow models. GitHub Repo TensorFlow Serving - A flexible, high-performance serving system for machine learning models, designed for production environments. GitHub Repo TensorFlow Extended (TFX) - An end-to-end platform for deploying production ML pipelines. GitHub Repo MLKit - A mobile SDK by Google that brings Google’s machine learning expertise to Android and iOS apps. GitHub Repo Ludwig - A deep learning toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code. GitHub Repo ONNX Runtime - A cross-platform inference and training machine-learning accelerator by Microsoft, compatible with models from many frameworks including PyTorch, TensorFlow, and more. GitHub Repo

AI Agents and Multi-Agent Systems

AutoGen - A framework by Microsoft for creating and managing multi-agent conversations, enabling the development of complex AI systems that can collaborate to achieve specific goals. GitHub Repo LangChain - An open-source framework designed to simplify the creation of applications that utilize language models, particularly for building agents that can interact with tools and APIs. GitHub Repo CrewAI - A framework that allows developers to create crews of AI agents, each with specific roles, to work collaboratively on tasks, enhancing productivity through delegation and teamwork. GitHub Repo AgentGPT - An experimental open-source project that allows users to create autonomous AI agents capable of completing tasks by breaking them down into subtasks and executing them. GitHub Repo BabyAGI - A Python-based task management system that uses AI to create, prioritize, and execute tasks autonomously, inspired by the concept of AGI but focused on baby steps towards it. GitHub Repo Jarvis - An open-source project for creating personal AI assistants that can understand commands, manage tasks, and interact with various systems, inspired by the AI from Iron Man. GitHub Repo

New AI Tools and Frameworks

Hugging Face Diffusers - A library for state-of-the-art diffusion models, which are used for generating high-quality images from textual descriptions, part of the broader trend towards generative AI. GitHub Repo Open Interpreter - A tool that allows the execution of code based on natural language instructions, bridging the gap between human language and programming, particularly useful for AI agents. GitHub Repo Vanna.AI - An open-source tool for creating AI-powered data products, focusing on simplifying the process of turning data into insights with AI assistance. GitHub Repo PR-Agent - An AI tool designed to assist in the pull request process by providing automated code reviews, suggestions, and even fixing minor issues, enhancing developer productivity. GitHub Repo Aide - An AI assistant for developers that helps with code understanding, generation, and debugging by integrating with IDEs, improving coding efficiency. GitHub Repo Mitra - An open-source project for conversational AI, focusing on creating chatbots that can understand and respond in multiple languages and dialects. GitHub Repo Devon - An AI code assistant that integrates with development environments to provide real-time coding help, from writing code to explaining complex concepts. GitHub Repo evoninja - A tool for evolutionary algorithms, allowing for optimization and search in complex problem spaces using AI techniques, which can be particularly useful for AI agents in decision-making. GitHub Repo GPT Researcher - A tool that leverages large language models to perform research tasks, from gathering information to summarizing findings, useful for creating research-oriented AI agents. GitHub Repo Semantic Kernel - Microsoft’s open-source SDK that enables developers to integrate AI into traditional programming patterns, particularly for crafting AI agents that can reason and plan. GitHub Repo Bark - An open-source text-to-speech model by Suno AI that can generate highly realistic, multilingual speech, representing the latest in voice synthesis technology. GitHub Repo Stable Diffusion - While not entirely new, its ongoing development includes features like improved image quality, faster inference, and better control over the generation process, making it a staple in AI-generated visuals. GitHub Repo Phi-2 - An open-source project by Microsoft focusing on small, efficient language models that can run on devices with limited computational resources, advancing the field of edge AI. GitHub Repo Vicuna - An open-source chatbot model trained by fine-tuning LLaMA on user-shared conversations, which brings conversational capabilities closer to real-world applications. GitHub Repo

AI Agents and Multi-Agent Systems

SuperAGI - An open-source platform that enables the creation of autonomous AI agents capable of self-improvement, memory management, and interaction with the real world through APIs. GitHub Repo AutoGPT - An experimental project that allows users to create and manage autonomous agents that can perform tasks by breaking them down into steps and executing them with minimal human intervention. GitHub Repo ChatArena - A framework for building multi-agent chat systems where agents can debate, collaborate, or compete, providing a platform for complex conversational AI interactions. GitHub Repo AgentForge - An open-source initiative for building custom AI agents that can interact with various services, manage workflows, and automate decision-making processes. GitHub Repo Orca - A project for developing AI agents that can learn from human demonstrations and feedback, aiming to create agents that can perform tasks in a more human-like manner. GitHub Repo

New AI Tools and Frameworks

Grok - An AI developed by xAI, designed to provide helpful and truthful answers, showcasing advancements in conversational AI with a focus on accelerating human scientific discovery. GitHub Repo NVIDIA NeMo Guardrails - An open-source toolkit for adding safety and reliability to conversational AI models, ensuring that AI responses are within defined ethical and operational boundaries. GitHub Repo Replit AI - An AI-powered coding assistant integrated into Replit’s online IDE, offering real-time code suggestions, explanations, and debugging, enhancing the coding experience for developers. GitHub Repo Griptape - A framework for building AI-driven applications that focus on structured data processing, natural language processing, and integrating AI into business workflows. GitHub Repo OpenLLaMA - An open-source project aiming to replicate the capabilities of Meta’s LLaMA model, providing the community with a large language model for research and development. GitHub Repo PaLM 2 - While not open-source, Google’s release of PaLM 2 API access has spurred related open-source projects and tools for leveraging its capabilities in various applications. GitHub Repo Dolly - An open-source project by Databricks that fine-tunes models like GPT-J for instruction following, making it easier to build AI that can understand and execute user commands. GitHub Repo CodeGen - An open-source model by Salesforce for generating code from natural language descriptions, which has seen significant interest for automating software development tasks. GitHub Repo MosaicML - Provides tools and frameworks for training large-scale machine learning models efficiently, with a focus on making AI model training more accessible. GitHub Repo Modular AI - A platform that offers tools for creating modular AI systems, allowing developers to build, share, and integrate AI components easily. GitHub Repo H2O Wave - A Python framework by H2O.ai for building real-time, interactive AI applications, focusing on user interface development for AI-driven insights. GitHub Repo Lightning AI - PyTorch Lightning’s evolution into a broader AI framework, offering tools for scaling AI from research to production with ease. GitHub Repo OpenAssistant - An open-source project by LAION aiming to create a conversational AI assistant that rivals commercial solutions, with transparency in its training data and model architecture. GitHub Repo GigaGAN - An advancement in Generative Adversarial Networks by NVIDIA, focusing on generating high-quality images with better scalability and efficiency. GitHub Repo AI21 Labs’ Jurassic-2 - While primarily a commercial offering, the open-source community has developed tools around its API for various applications, enhancing text generation capabilities. GitHub Repo

Computer Vision

Open3D - A modern library for 3D data processing, including 3D reconstruction, visualization, and machine learning on 3D data. GitHub Repo PCL (Point Cloud Library) - Focused on 2D/3D image and point cloud processing, PCL is used for tasks like object recognition, segmentation, and scene understanding. GitHub Repo SimpleCV - While mentioned before, it’s worth noting again for its simplicity in integrating computer vision into Python applications with a high-level interface. GitHub Repo PyTorch3D - A library for deep learning with 3D data, built on PyTorch, offering tools for 3D shape analysis, rendering, and more. GitHub Repo DeepLabCut - An open-source tool for markerless pose estimation of animals performing various tasks, using deep learning. GitHub Repo

Natural Language Processing (NLP)

Flair - Beyond its earlier mention, Flair has evolved to include advanced NLP capabilities like text classification, named entity recognition, and relation extraction. GitHub Repo Stanza - By Stanford NLP Group, it’s a modern Python library for NLP, offering tokenization, multi-word token expansion, lemmatization, and more. GitHub Repo Nemo - NVIDIA’s toolkit for conversational AI, which includes tools for speech recognition, natural language understanding, and text-to-speech. GitHub Repo

Reinforcement Learning

Sample Factory - A high-performance reinforcement learning framework that focuses on achieving high throughput for training RL agents. GitHub Repo Garage - A toolkit for reproducible reinforcement learning research, providing implementations of many RL algorithms. GitHub Repo

General AI and Machine Learning

TensorFlow Probability - An extension of TensorFlow offering probabilistic modeling and inference capabilities, useful for Bayesian machine learning. GitHub Repo PyTorch Lightning - While part of the PyTorch ecosystem, it deserves mention for its role in simplifying the creation of complex AI models by abstracting away boilerplate code. GitHub Repo Optuna - A hyperparameter optimization framework that can be used with various machine learning libraries, not just limited to a specific one. GitHub Repo MLJAR - An automated machine learning tool that helps in creating and tuning machine learning models without deep technical knowledge. GitHub Repo Cleanlab - A Python library for learning with noisy labels, data-centric AI, and improving datasets for better machine learning performance. GitHub Repo

Data Science and Analysis

Vaex - Mentioned earlier but worth highlighting for its ability to handle out-of-core DataFrames for visualization and machine learning on large datasets. GitHub Repo Polars - A blazingly fast DataFrames library for Rust and Python, optimized for performance and memory efficiency, useful for data preprocessing in AI projects. GitHub Repo Ibis - A productivity-centric Python framework that translates DataFrame operations into SQL, useful for data scientists working with SQL databases in AI workflows. GitHub Repo

AI Ethics and Fairness

Aequitas - A tool for auditing bias and fairness in machine learning models, helping developers understand and mitigate bias in their AI applications. GitHub Repo Themis - An open-source tool for fairness in machine learning, providing metrics and methods to assess and improve fairness in predictive models. GitHub Repo

Robotics and AI

ROS 2 (Robot Operating System 2) - While not exclusively AI, ROS 2 integrates AI for robotics, offering a framework for building robot applications with AI capabilities. GitHub Repo PyRobot - A Python library for robot application development, which includes AI for tasks like navigation, manipulation, and perception. GitHub Repo

Generative AI

StyleGAN3 - The latest iteration from NVIDIA in their StyleGAN series, focusing on improved quality and control over generated images. GitHub Repo DALL-E Mini - An open-source project inspired by DALL-E, allowing for text-to-image generation, though less sophisticated, it’s accessible for experimentation. GitHub Repo

Miscellaneous

TensorTrade - An open-source Python framework for building, training, evaluating, and deploying custom trading algorithms using reinforcement learning and other AI techniques. GitHub Repo Ludwig - Previously mentioned, but it’s also worth noting for its ability to automate the deep learning process, allowing non-experts to build models. GitHub Repo TensorFlow Quantum - For those interested in quantum computing and AI, this library integrates quantum computing algorithms with TensorFlow. GitHub Repo

AI for Healthcare

MONAI (Medical Open Network for AI) - A PyTorch-based framework for deep learning in healthcare imaging, providing tools for developing and deploying AI models for medical image analysis. GitHub Repo TorchIO - A library for efficient loading, preprocessing, augmentation, and patch-based sampling of 3D medical images for deep learning. GitHub Repo OpenHealth - An initiative to provide open-source tools and datasets for health informatics, focusing on AI applications in personalized medicine and health prediction. GitHub Repo

AI for Finance

FinRL - An open-source framework that applies reinforcement learning to quantitative finance, allowing for the simulation of trading environments and the training of trading agents. GitHub Repo TensorTrade - Already mentioned, but it’s significant in the finance sector for its application of AI in algorithmic trading. GitHub Repo

AI for Education

EdPy - An educational Python library that introduces students to programming with machine learning concepts, making AI education accessible. GitHub Repo AI Education Toolkit by Microsoft - While not strictly open-source, Microsoft provides open educational resources and tools for teaching AI, including AI for Earth, which can be adapted for educational purposes. GitHub Repo

AI for Environmental Science

GeoPandas - Extends the capabilities of Pandas to handle geospatial data, which can be used in AI projects focusing on environmental analysis, climate modeling, etc. GitHub Repo EcoAssist - An open-source tool for ecological data analysis, utilizing AI for biodiversity assessment and conservation planning. GitHub Repo

AI for Cybersecurity

Malware Detection with Deep Learning - Various open-source projects focus on using deep learning to detect malware, like those using TensorFlow or PyTorch for creating models that identify malicious software patterns. GitHub Repo PyTorch Geometric Temporal - While general-purpose, it’s used in cybersecurity for anomaly detection in network traffic over time using graph neural networks. GitHub Repo

AI for Accessibility

Project Florence - A Microsoft initiative providing AI tools to enhance accessibility for people with disabilities, including tools for speech recognition and visual assistance, with some components being open-source. GitHub Repo Sign Language Processing - Various open-source projects like OpenSign or DeepSign focus on AI for sign language recognition and translation, aiding communication for the deaf community. GitHub Repo

AI for Creative Arts

Magenta - Google’s project on machine learning for art and music, providing tools and models for generating creative content. GitHub Repo Artbreeder - An open-source project that uses AI for image blending and creation, allowing users to generate new art based on existing images. GitHub Repo

AI for Legal Tech

Contract Understanding Atticus Project (CUAP) - An initiative to use AI for understanding and analyzing legal contracts, making legal documents more accessible. GitHub Repo LexPredict - While more of a company, they contribute to open-source projects like ‘contraxsuite’, which uses AI for contract analysis and review. GitHub Repo

AI for Social Good

AIcrowd - A platform for AI challenges focused on social impact, where many projects and datasets are open-sourced for community engagement in solving global issues. GitHub Repo DataKind - An organization that brings data science and AI to social causes, with open-source projects tackling issues like disaster response, health, and education. GitHub Repo

AI for Autonomous Systems

CARLA - An open-source simulator for autonomous driving research, providing a platform to test AI algorithms in virtual urban environments. GitHub Repo AirSim - Microsoft’s open-source simulator for AI research in autonomous vehicles, drones, and more, built on Unreal Engine. GitHub Repo

AI for Explainability and Interpretability

Anchors - A technique for model interpretability, providing model-agnostic explanations that are easy to understand. GitHub Repo Alibi - An open-source Python library focused on AI interpretability, providing methods like CEM (Contrastive Explanation Method) and ALE (Accumulated Local Effects). GitHub Repo

AI for Disaster Management

QGIS - While primarily a Geographic Information System (GIS), QGIS has plugins and extensions developed by the community for AI-driven disaster risk analysis and mapping. GitHub Repo InaSAFE - An open-source plugin for QGIS that uses AI for impact analysis of natural disasters, helping in planning and response strategies. GitHub Repo

AI for Agriculture

AgriBot - An open-source project focusing on AI-driven robotics for precision agriculture, including crop monitoring, soil analysis, and automated harvesting. GitHub Repo PlantCV - A plant phenotyping software package that uses computer vision and machine learning to analyze plant images for agricultural research. GitHub Repo

AI for Urban Planning

UrbanFootprint - An open-source platform that leverages AI for urban analysis, planning, and simulation, providing tools for developers and city planners to make data-driven decisions. GitHub Repo CityEnergyAnalyst - An open-source tool for urban energy system modeling, which integrates AI for optimizing energy use in city planning. GitHub Repo

AI for Privacy and Security

OpenMined - While mentioned previously with PySyft, OpenMined is broader, focusing on privacy-preserving AI technologies, including federated learning for data privacy. GitHub Repo FATE (Federated AI Technology Enabler) - An open-source project by WeBank for federated learning, enhancing data privacy in AI model training across different institutions. GitHub Repo

AI for Quantum Computing

Qiskit - IBM’s open-source framework for quantum computing, which includes tools for integrating quantum algorithms with classical machine learning for hybrid quantum-classical AI solutions. GitHub Repo Cirq - Google’s open-source framework for creating, editing, and invoking Noisy Intermediate Scale Quantum (NISQ) circuits, with potential applications in AI for optimization and simulation tasks. GitHub Repo

AI for Synthetic Data Generation

Synthetic Data Vault (SDV) - An open-source library for generating synthetic data that preserves the statistical properties of real data, useful for training AI models without compromising privacy. GitHub Repo Gretel Synthetics - Focused on creating high-quality synthetic data for machine learning, with tools for data anonymization and augmentation. GitHub Repo

AI for Accessibility and Inclusion

Project Euphonia - Google’s initiative with some open-source components for improving speech recognition for people with speech impairments, aiming to make AI more inclusive. GitHub Repo Includia - An open-source project aimed at using AI to make digital content more accessible, focusing on automated captioning, audio descriptions, and sign language translation. GitHub Repo

AI for Game Development

ML-Agents - Unity’s open-source toolkit for integrating machine learning into game development, allowing for the creation of AI-driven game characters and environments. GitHub Repo TensorFlow for Game Developers - While not a single project, there are multiple open-source initiatives showcasing how TensorFlow can be used in game AI, from NPC behavior to procedural content generation. GitHub Repo

AI for Scientific Research

DeepChem - An open-source framework for drug discovery, materials science, and other scientific domains using deep learning. GitHub Repo AI Feynman - An open-source project that uses symbolic regression and neural networks to discover mathematical equations from data, aiding in scientific discovery. GitHub Repo

AI for Social Media Analysis

Tweepy - An open-source Python library for accessing the Twitter API, often used in projects for AI-driven social media analysis, sentiment analysis, and trend prediction. GitHub Repo TextRazor - While offering commercial services, TextRazor provides some open-source tools for natural language processing on social media content, focusing on entity extraction, topic tagging, etc. GitHub Repo

AI for Healthcare

OpenMHealth - A platform for creating and sharing mobile health data tools, leveraging AI for personalized health insights. GitHub Repo Cardiomedic - Uses AI to analyze ECG data for early detection of cardiovascular diseases. GitHub Repo DeepLesion - An AI project focused on detecting, segmenting, and classifying lesions in medical imaging. GitHub Repo CheXNet - An open-source deep learning algorithm for diagnosing pneumonia from chest X-rays. GitHub Repo NeuroFlow - An AI platform for mental health, providing predictive analytics for mental health interventions. GitHub Repo DeepBrain - An AI tool for brain tumor segmentation from MRI scans. GitHub Repo DIG (DeepInsightGraph) - A framework for graph-based AI in drug discovery, focusing on predicting drug-target interactions. GitHub Repo AI4MedImaging - A collection of AI tools for various medical imaging tasks, from segmentation to classification. GitHub Repo Syglass - An open-source VR platform for medical image visualization, which can incorporate AI for enhanced analysis. GitHub Repo OpenDenoising - AI solutions for reducing noise in medical images, improving diagnostic accuracy. GitHub Repo

AI for Finance

QuantStats - An open-source Python library for portfolio and risk analytics, integrating AI for predictive analysis. GitHub Repo PyFolio - A library for portfolio and risk analytics in Python, with AI-driven performance attribution. GitHub Repo Zipline - Quantitative trading library by Quantopian, now open-source, with AI integration for backtesting trading strategies. GitHub Repo Catalyst - A high-performance backtesting and trading library for digital assets, incorporating AI for strategy optimization. GitHub Repo Backtrader - A feature-rich framework for trading strategy development, backtesting, and execution with AI enhancements. GitHub Repo Freqtrade - An open-source cryptocurrency trading bot that uses AI for strategy optimization. GitHub Repo gym-trading - A set of environments for reinforcement learning in trading, based on OpenAI’s Gym. GitHub Repo ML-Finance - A collection of machine learning models applied to financial data analysis. GitHub Repo PyAlgoTrade - An event-driven backtesting and paper trading library with AI capabilities for strategy development. GitHub Repo Tensorflow Finance - Integrates TensorFlow with financial time series analysis for predictive modeling. GitHub Repo

AI for Education

Khan Academy AI - While not all open-source, Khan Academy shares some AI tools for educational content personalization. GitHub Repo AI4K12 - An initiative for integrating AI education into K-12 curricula, providing open-source educational resources. GitHub Repo Teachable Machine - Google’s project for teaching basic machine learning concepts in an accessible way, with open-source components. GitHub Repo AI Education Hub - An open platform offering resources, tutorials, and projects for learning AI, supported by community contributions. GitHub Repo Blockly - Google’s visual programming tool, which has been adapted for teaching AI concepts through block-based coding. GitHub Repo ScratchAI - An extension of Scratch for teaching AI through visual programming, focusing on machine learning basics. GitHub Repo Machine Learning for Kids - An educational platform with open-source elements for teaching young students about AI through fun projects. GitHub Repo AI School - An open-source initiative providing courses and practical projects in AI for high school and college students. GitHub Repo Code.org AI for Oceans - An educational game where students use AI to solve puzzles, with educational resources being open-source. GitHub Repo AI Adventures - Google’s educational series on AI, with some open-source code examples for teaching AI concepts. GitHub Repo

AI for Environmental Science

EcoData - An AI platform for environmental data analysis, focusing on climate change and biodiversity. GitHub Repo ForestWatcher - Uses AI for real-time monitoring of deforestation through satellite imagery analysis. GitHub Repo AWhere - An open-source project for agricultural weather analytics, leveraging AI for predictive farming. GitHub Repo OpenET - An AI-driven platform for evapotranspiration mapping, aiding in water resource management. GitHub Repo MarineDebrisTracker - An AI tool for tracking and classifying marine debris through citizen science initiatives. GitHub Repo

PyreCheck - An AI-based tool for static analysis of Python code to detect security vulnerabilities. GitHub Repo DeepLog - Utilizes deep learning for anomaly detection in system logs, enhancing cybersecurity by identifying unusual patterns. GitHub Repo KITNET - A lightweight neural network for real-time network intrusion detection, focusing on efficiency and accuracy. GitHub Repo MalGAN - An adversarial approach to malware detection, using GANs to generate and detect malware samples. GitHub Repo SecML - A library for secure and robust machine learning, including adversarial machine learning for cybersecurity applications. GitHub Repo AI-Cyber - An initiative providing tools and datasets for AI in cybersecurity, with a focus on threat detection and response. GitHub Repo OpenCAN - A project aimed at using AI for Content Anomaly Detection in network traffic to prevent data exfiltration. GitHub Repo ThreatPlaybook - An open-source framework that uses AI to automate and enhance threat hunting processes. GitHub Repo Sigma - While primarily a rule-based system, it’s increasingly integrated with AI for more dynamic threat detection. GitHub Repo DeepPhish - An AI model for detecting phishing websites by analyzing various features of web pages. GitHub Repo

AI for Accessibility and Inclusion

a11yTools - A suite of AI tools for improving web accessibility, including automated testing and suggestions for improvements. GitHub Repo VoiceVox - An open-source text-to-speech software with AI capabilities, designed to be highly accessible for visually impaired users. GitHub Repo SignAll - An AI project for real-time sign language translation, aiming to bridge communication gaps. GitHub Repo A11yWatch - Uses AI to monitor and improve website accessibility in real-time, providing developers with actionable insights. GitHub Repo ReadSpeaker - An open-source initiative for text-to-speech, focusing on making digital content accessible through AI. GitHub Repo AccessiBe - While offering commercial services, they contribute to open-source projects for AI-driven web accessibility solutions. GitHub Repo eSSENTIAL Accessibility - Provides an AI-powered platform for creating accessible websites, with some open-source components. GitHub Repo WebAIM - Offers tools and resources for web accessibility, including AI-driven analysis tools for improving site usability. GitHub Repo A11ygator - An open-source tool that uses AI to analyze websites for accessibility compliance and issues. GitHub Repo Be My AI - An AI assistant for visually impaired users, helping with object recognition and navigation through voice commands. GitHub Repo

AI for Creative Arts

DeepArt - An open-source project for transforming photos into artwork using neural style transfer. GitHub Repo AIVA - An AI composing music, with open-source tools for music generation and analysis. GitHub Repo ArtEngine - A platform for AI-generated art, providing tools for artists to experiment with AI in their creative process. GitHub Repo DeepDream - Google’s project for generating dream-like images from neural networks, now with community-driven open-source implementations. GitHub Repo Obvious - An art collective that uses AI to create art, with open-source code for some of their generative models. GitHub Repo MuseGAN - A GAN-based approach for music generation, allowing for the creation of multi-track compositions. GitHub Repo Deep-Speech - While primarily for speech recognition, it’s been adapted for creative projects like AI-generated poetry readings. GitHub Repo VQ-VAE-2 - An advanced version of Vector Quantized Variational Autoencoder for high-quality image generation, used in creative AI projects. GitHub Repo TextGenRNN - An open-source project for generating text, which has been used for creative writing and poetry. GitHub Repo ThisPersonDoesNotExist - Utilizes StyleGAN for generating realistic human faces, with open-source variants for different applications. GitHub Repo

AI for Legal Tech

Legaltech-AI - A repository of AI tools for legal document analysis, contract review, and case prediction. GitHub Repo DocuSign-AI - While DocuSign is commercial, they’ve contributed to open-source AI for document understanding in legal contexts. GitHub Repo Ross Intelligence - An AI legal research tool with some open-source components for natural language processing in legal texts. GitHub Repo CaseText - Offers an open-source AI tool for legal research, focusing on case law analysis and prediction. GitHub Repo OpenLaw - A platform for legal agreements using blockchain, with AI integration for smart contract analysis. GitHub Repo Kira Systems - Known for contract analysis, they’ve shared some AI models for legal document review. GitHub Repo LexisNexis AI - While primarily commercial, they contribute to open-source projects for legal AI, especially in document classification. GitHub Repo Legal Robot - An AI tool for making legal documents more accessible and efficient. GitHub Repo