Collection of google colaboratory notebooks for fast and easy experiments
Python
1,664
75 commits
updated Aug 6, 2026
The page might not be rendered properly. Please open README.md file directly
| repositories | papers | packages |
|---|---|---|
|
|
|
| name | description | authors | links | colaboratory | update |
|---|---|---|---|---|---|
| Python for Algorithmic Trading Cookbook | From raw market data to live algorithmic trading through 68 hands-on recipes across 15 chapters | Packt |  |  | 23.05.2026 |
| Time Series with PyTorch | Starting with PyTorch fundamentals, you will build neural networks from scratch and progress through recurrent networks, attention mechanisms, and transformers before exploring forecasting architectures such as N-BEATS, N-HiTS, and the Temporal Fusion Transformer | Packt |  | | 08.05.2026 |
| GPU Computing with Python 3 and CUDA | How to accelerate Python applications using NVIDIA’s CUDA platform and a modern ecosystem of Python tools and libraries | Packt |  | | 11.04.2026 |
| The Autodiff Cookbook | You'll go through a whole bunch of neat autodiff ideas that you can cherry pick for your own work, starting with the basics |  | | 01.04.2026 | |
| Practical RL | An open course on reinforcement learning in the wild | 
| | 05.03.2026 | |
| Deep Learning School course (ML + CV) | Nina Konovalova |  | | 04.03.2026 | |
| mlcourse.ai | Open Machine Learning Course | Yury Kashnitsky |  | | 24.01.2026 |
| Udacity Deep Learning class with TensorFlow | Learn how to apply deep learning to solve complex problems | Mark Daoust |  | | 14.01.2026 |
| Курс "Машинное обучение" на ФКН ВШЭ | Конспекты лекций, материалы семинаров и домашние задания (теоретические, практические, соревнования) по курсу "Машинное обучение", проводимому на бакалаврской программе "Прикладная математика и информатика" Факультета компьютерных наук Высшей школы экономики | Evgeny Sokolov |  | | 14.09.2025 |
| XAI | Дearning explainable artificial intelligence methods | Сабрина Садиех |  | | 05.09.2025 |
| LLM Engineering Essentials course | 12-week course, created by experts from academia and industry, is designed specifically for developers and engineers | others |  | | 22.05.2025 |
| Understanding Language Models | Course deals with language models, in particular (but not exclusively so) on transformer-based language models like GPT-x or LLama |  | | 17.04.2025 | |
| Introduction to Deep Learning course | Tatiana Gaintseva | 
| | 24.01.2025 | |
| ARENA | Provide talented individuals with the skills, tools, and environment necessary for upskilling in ML engineering, for the purpose of contributing directly to AI alignment in technical roles | Callum McDougall |  | | 30.12.2024 |
| Deep Learning Course at the University of Amsterdam | Series of Jupyter notebooks that are designed to help you understanding the "theory" from the lectures by seeing corresponding implementations |  | | 17.10.2024 | |
| Machine Learning Simplified | A Gentle Introduction to Supervised Learning | Andrew Wolf | 
| | 29.08.2024 |
| Anthropic courses | Anthropic's educational courses | Anthropic |  | | 22.08.2024 |
| Deep RL Course | The Hugging Face Deep Reinforcement Learning Course | 
| | 24.06.2024 | |
| Anthropic's Prompt Engineering Interactive Tutorial | Course is intended to provide you with a comprehensive step-by-step understanding of how to engineer optimal prompts within Claude | Anthropic | 
| | 02.04.2024 |
| Generative AI for Beginners - A Course | A 12 Lesson course teaching everything you need to know to start building Generative AI applications | microsoft |  | | 22.02.2024 |
| Deep Reinforcement Learning | CS 285 at UC Berkeley |  | | 29.08.2023 | |
| npNLG | The course introduces the basics of NLG, neural language models and their implementation in PyTorch, as well as a selection of recent pragmatic neural NLG approaches | Michael Franke |  | | 09.11.2022 |
| DSP theory | Theory of digital signal processing: signals, filtration (IIR, FIR, CIC, MAF), transforms (FFT, DFT, Hilbert, Z-transform) etc |  | | 18.10.2022 | |
| Machine learning course | This course is broad and shallow, but author will provide additional links so that you can deepen your understanding of the ML method you need | Тимчишин Віталій | 
| | 02.09.2021 |
| Intro to TensorFlow for Deep Learning | Dive into deep learning with this practical course on TensorFlow and the Keras API | | | 09.09.2020 | |
| Introduction to TensorFlow Lite | Learn how to deploy deep learning models on mobile and embedded devices with TensorFlow Lite | | | 09.09.2020 | |
| NYU-DLSP20 | This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition | 
| | 30.10.2019 |
| name | description | authors | links | colaboratory | update |
|---|---|---|---|---|---|
| Kornia | Library is composed by a subset of packages containing operators that can be inserted within neural networks to train models to perform image transformations, epipolar geometry, depth estimation, and low-level image processing such as filtering and edge detection that operate directly on tensors |  | | 05.08.2026 | |
| Retrieval based Voice Conversion WebUI | An easy-to-use Voice Conversion framework based on VITS | 源文雨 | 
| | 04.08.2026 |
| SGLang | System comprising a frontend language and runtime for efficiently programming and executing complex structured language model programs with optimizations for cache reuse and structured output decoding. |  | | 04.08.2026 | |
| SHAP | SHapley Additive exPlanations is a game theoretic approach to explain the output of any machine learning model | 
| | 03.08.2026 | |
| YOLOv8 | State-of-the-art model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility | Glenn Jocher |  | | 01.08.2026 |
| YOLOv3 | You Only Look Once | Glenn Jocher | 
| | 29.07.2026 |
| YOLOv5 | You Only Look Once | Glenn Jocher | 
| | 29.07.2026 |
| dm_control | DeepMind Infrastructure for Physics-Based Simulation | 
| | 28.07.2026 | |
| ADK | Collection provides ready-to-use agents built on top of the Agent Development Kit, designed to accelerate your development process |  | | 24.07.2026 | |
| OmegaConf | Hierarchical configuration system, with support for merging configurations from multiple sources providing a consistent API regardless of how the configuration was created | Omry Yadan | 
| | 22.07.2026 |
| Agent Starter Pack | Collection of production-ready Generative AI Agent templates built for Google Cloud | Kristopher Overholt | 
| | 21.07.2026 |
| AlphaFold | Highly accurate protein structure prediction | 
| | 14.07.2026 | |
| GigaAM | SSL pretraining framework that leverages masked language modeling with targets derived from a speech recognition model | 
| | 14.07.2026 | |
| s | This paper introduces O-Voxel, a new sparse voxel representation and compression framework that enables high-fidelity, efficient 3D asset generation with flexible geometry and detailed appearance from learned compact latent spaces |  | | 09.07.2026 | |
| NeMo | A conversational AI toolkit built for researchers working on automatic speech recognition, natural language processing, and text-to-speech synthesis | 
| | 07.07.2026 | |
| Anime Face Detector | Anime Face Detector using mmdet and mmpose | hysts | 
| | 05.07.2026 |
| Chronos-2 | Pretrained, zero-shot time series forecasting model that uses group attention and synthetic multivariate training to perform univariate, multivariate, and covariate-informed forecasting with state-of-the-art accuracy across diverse real-world benchmarks. |  | | 02.07.2026 | |
| Nano Banana | An image generation and editing model powered by generative artificial intelligence and developed by Google DeepMind | Guillaume Vernade | | 30.06.2026 | |
| Presidio | Context aware, pluggable and customizable PII de-identification service for text and images | Omri Mendels |  | | 28.06.2026 |
| Weaver | Lightweight autoregressive adapter for factorized draft models that constructs proposal trees from top-K marginals to restore conditional dependencies and enable faster speculative decoding with optimized tree verification and CUDA kernels in SGLang. |  | | 24.06.2026 | |
| TransformerLens | Library for doing mechanistic interpretability of GPT-2 Style language models | 
| | 22.06.2026 | |
| Hyperopt | Python library for serial and parallel optimization over awkward search spaces, which may include real-valued, discrete, and conditional dimensions |  | | 21.06.2026 | |
| highway-env | A collection of environments for autonomous driving and tactical decision-making tasks | Edouard Leurent | 
| | 19.06.2026 |
| SentencePiece | An unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training | 
| | 14.06.2026 | |
| RF-DETR | Lightweight, real-time detection transformer that uses weight-sharing neural architecture search to automatically discover optimal accuracy-latency tradeoffs for object detection across diverse target datasets. |
|  | | 13.06.2026 |
| Mem0 | Self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users |  | | 13.06.2026 | |
| Swarm | Educational framework exploring ergonomic, lightweight multi-agent orchestration | others | 
| | 07.06.2026 |
| Duo | This software project implements Duo, a diffusion-based language modeling framework that improves discrete diffusion text generation using Gaussian-guided curriculum learning and Discrete Consistency Distillation for faster training and few-step sampling. |  | | 03.06.2026 | |
| Magenta RT | An open-weights live music model that allows you to interactively create, control and perform music in the moment | Chris Donahue |  | | 02.06.2026 |
| TorchGeo | PyTorch domain library that provides datasets, transforms, samplers, and pre-trained models specific to geospatial data |  | | 01.06.2026 | |
| pymdp | Package for simulating Active Inference agents in Markov Decision Process environments | others |  | | 29.05.2026 |
| ActionMesh | Temporal 3D diffusion framework that generates production-ready, topology-consistent animated 3D meshes from inputs like video, text, or static 3D shapes in a fast, feed-forward manner. |  | | 28.05.2026 | |
| Lyria 2 | Delivers high-fidelity music and professional-grade audio, capturing subtle nuances across a range of genres and intricate compositions | Katie Nguyen | | 13.05.2026 | |
| Video Seal | Comprehensive framework for neural video watermarking and a competitive open-sourced model | 
| | 11.05.2026 | |
| Google Cloud Text-to-Speech | Enables easy integration of Google text recognition technologies into developer applications |  | | 07.05.2026 | |
| Imagen 4 | Text-to-image model, with photorealistic images, near real-time speed, and sharper clarity | Katie Nguyen | | 06.05.2026 | |
| CrewAI | Lean, lightning-fast Python framework built entirely from scratch—completely independent of LangChain or other agent frameworks | João Moura |  | | 20.04.2026 |
| CodeGemma | How to load, fine-tune and deploy CodeGemma model on SQL by utilising Hugging Face | Carlo Fisicaro | | 20.04.2026 | |
| Hello, many worlds | This tutorial shows how a classical neural network can learn to correct qubit calibration errors | Michael Broughton |
| | 18.04.2026 |
| Text Generation Web UI | The best local UI for large language models, with easy setup and powerful features. 100% offline. | oobabooga |  | | 13.04.2026 |
| DataChain | AI-dataframe to enrich, transform and analyze data from cloud storages for ML training and LLM apps | Daniel K |  | | 13.04.2026 |
| JAX MD | Differentiable physics and molecular dynamics simulation framework in JAX that enables scalable, GPU-accelerated simulations and end-to-end optimization of entire trajectories, with flexible primitives and neural network integration. |  | | 05.04.2026 | |
| GraphCast | Learning skillful medium-range global weather forecasting |  | | 30.03.2026 | |
| ignite | High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently. | Anmol Joshi |  | | 25.03.2026 |
| edgeai-tensorlab | Edge AI Model Development Tools | Manu | 
| | 25.03.2026 |
| Dopamine | Research framework for fast prototyping of reinforcement learning algorithms |  | | 24.03.2026 | |
| autoresearch | Bilevel Autoresearch is a bilevel autoresearch framework in which an outer autoresearch loop reads and modifies the code and traces of an inner autoresearch loop to inject new Python search mechanisms at runtime, thereby improving the inner loop’s task search behavior without changing the underlying LLM. | Andrej Karpathy |  | | 19.03.2026 |
| Opik | From RAG chatbots to code assistants to complex agentic pipelines and beyond, build LLM systems that run better, faster, and cheaper with tracing, evaluations, and dashboards | Jacques Verré |  | | 19.03.2026 |
| PEFT | Parameter-Efficient Fine-Tuning methods enable efficient adaptation of pre-trained language models to various downstream applications without fine-tuning all the model's parameters | 
| | 17.03.2026 | |
| tada | Generative text-to-speech and spoken language modeling framework that introduces a one-to-one synchronized text-acoustic tokenization scheme for unified large language model-based speech modeling with reduced hallucinations and inference cost. |  | | 16.03.2026 | |
| spiky | This project introduces a spiking neural network paradigm that reframes modern AI models in terms of spike-based polychronization to achieve combinatorially large encoding capacity and dramatically higher energy efficiency than conventional artificial neural networks. | Anatoli S tarostin | 
| | 14.03.2026 |
| DeepFloyd IF | State-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding | others | 
| | 12.03.2026 |
| Diffusers | Provides pretrained diffusion models across multiple modalities, such as vision and audio, and serves as a modular toolbox for inference and training of diffusion models | Hugging Face | 
| | 12.03.2026 |
| CatBoost | High-performance open source library for gradient boosting on decision trees | others |  | | 09.03.2026 |
| BEiT | Self-supervised vision representation model, which stands for Bidirectional Encoder representation from Image Transformers | 
| | 07.03.2026 | |
| Diffusion_models_tutorial | This project develops diffusion probabilistic models for high-quality image synthesis, leveraging a new connection to denoising score matching with Langevin dynamics to achieve state-of-the-art generative performance and a progressive lossy decompression scheme. |  | | 05.03.2026 | |
| HACRL-code | This paper presents Heterogeneous Agent Collaborative Reinforcement Learning, a Reinforcement Learning from Verifiable Reward framework in which heterogeneous agents share verified rollouts during training to collaboratively optimize while still executing independently at inference time. |  | | 05.03.2026 | |
| ExecuTorch | PyTorch's unified solution for deploying AI models on-device, from smartphones to microcontrollers, built for privacy, performance, and portability | SaoirseARM |  | | 04.03.2026 |
| PaperBanana | Agentic framework that uses advanced vision-language and image-generation models to automatically create and refine publication-ready academic illustrations, evaluated on a new benchmark of methodology diagrams and statistical plots. |  | | 03.03.2026 | |
| GigaAgent | Универсальный агент-оркестратор для решения широкого круга задач (ReAct + REPL) | Mikelarg |  | | 26.02.2026 |
| Giskard | Open-source library to detect hallucinations and security issues to turn them into test suites that you can automatically execute | 
| | 17.02.2026 | |
| SGLang | Fast serving framework for large language models and vision language models | | | 15.02.2026 | |
| Thorsten-Voice | Free to use, offline working, high quality german TTS voice should be available for every project without any license struggling | Thorsten Müller |  | | 02.02.2026 |
| fastai | The fastai deep learning library | Sylvain Gugger |  | | 28.01.2026 |
| LM Evaluation Harness | Framework for few-shot evaluation of language models. | Lintang Sutawika | 
| | 27.01.2026 |
| OpenSpiel | Collection of environments and algorithms for research in general reinforcement learning and search/planning in games | others
|  | | 22.01.2026 |
| Keras | Multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO (for inference-only) | François Chollet |  | | 21.01.2026 |
| Grounding DINO | Marrying DINO with Grounded Pre-Training for Open-Set Object Detection | 
| | 19.01.2026 | |
| GNN | Production-tested library for building GNNs at large scale | others
| 
| | 14.01.2026 |
| Gin Config | Lightweight configuration framework for Python, based on dependency injection |  | | 14.01.2026 | |
| PyGlove | General-purpose library for Python object manipulation |  | | 14.01.2026 | |
| Brax | A differentiable physics engine that simulates environments made up of rigid bodies, joints, and actuators | others |  | | 14.01.2026 |
| T5 | Text-To-Text Transfer Transformer |  | | 14.01.2026 | |
| SeqIO | Library for processing sequential data to be fed into downstream sequence models | others
| 
| | 14.01.2026 |
| TFDS | Collection of ready-to-use datasets for use with TensorFlow, Jax, and other Machine Learning frameworks | Ryan Sepassi | 
| | 14.01.2026 |
| TensorFlow Privacy | Library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy | 
| | 14.01.2026 | |
| TF-Agents | A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning | 
| | 14.01.2026 | |
| Reverb | Efficient and easy-to-use data storage and transport system designed for machine learning research | others | 
| | 14.01.2026 |
| ACME | A library of reinforcement learning components and agents | 
| | 14.01.2026 | |
| Gemma | Family of open-weights Large Language Model by Google DeepMind, based on Gemini research and technology |  | | 14.01.2026 | |
| Sonnet | Library built on top of TensorFlow 2 designed to provide simple, composable abstractions for machine learning research | others
|
Truncated — view the full README on GitHub.
247 followers · starred Oct 2021
26 followers · starred Apr 2023
120 followers · starred May 2023
2,531 followers · starred Oct 2023
Collection of google colaboratory notebooks for fast and easy experiments
Python
1,664
75 commits
updated Aug 6, 2026
The page might not be rendered properly. Please open README.md file directly
| repositories | papers | packages |
|---|---|---|
|
|
|
| name | description | authors | links | colaboratory | update |
|---|---|---|---|---|---|
| Python for Algorithmic Trading Cookbook | From raw market data to live algorithmic trading through 68 hands-on recipes across 15 chapters | Packt | | | 23.05.2026 |
| Time Series with PyTorch | Starting with PyTorch fundamentals, you will build neural networks from scratch and progress through recurrent networks, attention mechanisms, and transformers before exploring forecasting architectures such as N-BEATS, N-HiTS, and the Temporal Fusion Transformer | Packt | | | 08.05.2026 |
| GPU Computing with Python 3 and CUDA | How to accelerate Python applications using NVIDIA’s CUDA platform and a modern ecosystem of Python tools and libraries | Packt | | | 11.04.2026 |
| The Autodiff Cookbook | You'll go through a whole bunch of neat autodiff ideas that you can cherry pick for your own work, starting with the basics | | | 01.04.2026 | |
| Practical RL | An open course on reinforcement learning in the wild |
| | 05.03.2026 | |
| Deep Learning School course (ML + CV) | Nina Konovalova | | | 04.03.2026 | |
| mlcourse.ai | Open Machine Learning Course | Yury Kashnitsky | | | 24.01.2026 |
| Udacity Deep Learning class with TensorFlow | Learn how to apply deep learning to solve complex problems | Mark Daoust | | | 14.01.2026 |
| Курс "Машинное обучение" на ФКН ВШЭ | Конспекты лекций, материалы семинаров и домашние задания (теоретические, практические, соревнования) по курсу "Машинное обучение", проводимому на бакалаврской программе "Прикладная математика и информатика" Факультета компьютерных наук Высшей школы экономики | Evgeny Sokolov | | | 14.09.2025 |
| XAI | Дearning explainable artificial intelligence methods | Сабрина Садиех | | | 05.09.2025 |
| LLM Engineering Essentials course | 12-week course, created by experts from academia and industry, is designed specifically for developers and engineers | others | | | 22.05.2025 |
| Understanding Language Models | Course deals with language models, in particular (but not exclusively so) on transformer-based language models like GPT-x or LLama | | | 17.04.2025 | |
| Introduction to Deep Learning course | Tatiana Gaintseva |
| | 24.01.2025 | |
| ARENA | Provide talented individuals with the skills, tools, and environment necessary for upskilling in ML engineering, for the purpose of contributing directly to AI alignment in technical roles | Callum McDougall | | | 30.12.2024 |
| Deep Learning Course at the University of Amsterdam | Series of Jupyter notebooks that are designed to help you understanding the "theory" from the lectures by seeing corresponding implementations | | | 17.10.2024 | |
| Machine Learning Simplified | A Gentle Introduction to Supervised Learning | Andrew Wolf |
| | 29.08.2024 |
| Anthropic courses | Anthropic's educational courses | Anthropic | | | 22.08.2024 |
| Deep RL Course | The Hugging Face Deep Reinforcement Learning Course |
| | 24.06.2024 | |
| Anthropic's Prompt Engineering Interactive Tutorial | Course is intended to provide you with a comprehensive step-by-step understanding of how to engineer optimal prompts within Claude | Anthropic |
| | 02.04.2024 |
| Generative AI for Beginners - A Course | A 12 Lesson course teaching everything you need to know to start building Generative AI applications | microsoft | | | 22.02.2024 |
| Deep Reinforcement Learning | CS 285 at UC Berkeley | | | 29.08.2023 | |
| npNLG | The course introduces the basics of NLG, neural language models and their implementation in PyTorch, as well as a selection of recent pragmatic neural NLG approaches | Michael Franke | | | 09.11.2022 |
| DSP theory | Theory of digital signal processing: signals, filtration (IIR, FIR, CIC, MAF), transforms (FFT, DFT, Hilbert, Z-transform) etc | | | 18.10.2022 | |
| Machine learning course | This course is broad and shallow, but author will provide additional links so that you can deepen your understanding of the ML method you need | Тимчишин Віталій |
| | 02.09.2021 |
| Intro to TensorFlow for Deep Learning | Dive into deep learning with this practical course on TensorFlow and the Keras API | | | 09.09.2020 | |
| Introduction to TensorFlow Lite | Learn how to deploy deep learning models on mobile and embedded devices with TensorFlow Lite | | | 09.09.2020 | |
| NYU-DLSP20 | This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition |
| | 30.10.2019 |
| name | description | authors | links | colaboratory | update |
|---|---|---|---|---|---|
| Kornia | Library is composed by a subset of packages containing operators that can be inserted within neural networks to train models to perform image transformations, epipolar geometry, depth estimation, and low-level image processing such as filtering and edge detection that operate directly on tensors | | | 05.08.2026 | |
| Retrieval based Voice Conversion WebUI | An easy-to-use Voice Conversion framework based on VITS | 源文雨 |
| | 04.08.2026 |
| SGLang | System comprising a frontend language and runtime for efficiently programming and executing complex structured language model programs with optimizations for cache reuse and structured output decoding. | | | 04.08.2026 | |
| SHAP | SHapley Additive exPlanations is a game theoretic approach to explain the output of any machine learning model |
| | 03.08.2026 | |
| YOLOv8 | State-of-the-art model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility | Glenn Jocher | | | 01.08.2026 |
| YOLOv3 | You Only Look Once | Glenn Jocher |
| | 29.07.2026 |
| YOLOv5 | You Only Look Once | Glenn Jocher |
| | 29.07.2026 |
| dm_control | DeepMind Infrastructure for Physics-Based Simulation |
| | 28.07.2026 | |
| ADK | Collection provides ready-to-use agents built on top of the Agent Development Kit, designed to accelerate your development process | | | 24.07.2026 | |
| OmegaConf | Hierarchical configuration system, with support for merging configurations from multiple sources providing a consistent API regardless of how the configuration was created | Omry Yadan |
| | 22.07.2026 |
| Agent Starter Pack | Collection of production-ready Generative AI Agent templates built for Google Cloud | Kristopher Overholt |
| | 21.07.2026 |
| AlphaFold | Highly accurate protein structure prediction |
| | 14.07.2026 | |
| GigaAM | SSL pretraining framework that leverages masked language modeling with targets derived from a speech recognition model |
| | 14.07.2026 | |
| s | This paper introduces O-Voxel, a new sparse voxel representation and compression framework that enables high-fidelity, efficient 3D asset generation with flexible geometry and detailed appearance from learned compact latent spaces | | | 09.07.2026 | |
| NeMo | A conversational AI toolkit built for researchers working on automatic speech recognition, natural language processing, and text-to-speech synthesis |
| | 07.07.2026 | |
| Anime Face Detector | Anime Face Detector using mmdet and mmpose | hysts |
| | 05.07.2026 |
| Chronos-2 | Pretrained, zero-shot time series forecasting model that uses group attention and synthetic multivariate training to perform univariate, multivariate, and covariate-informed forecasting with state-of-the-art accuracy across diverse real-world benchmarks. | | | 02.07.2026 | |
| Nano Banana | An image generation and editing model powered by generative artificial intelligence and developed by Google DeepMind | Guillaume Vernade | | 30.06.2026 | |
| Presidio | Context aware, pluggable and customizable PII de-identification service for text and images | Omri Mendels | | | 28.06.2026 |
| Weaver | Lightweight autoregressive adapter for factorized draft models that constructs proposal trees from top-K marginals to restore conditional dependencies and enable faster speculative decoding with optimized tree verification and CUDA kernels in SGLang. | | | 24.06.2026 | |
| TransformerLens | Library for doing mechanistic interpretability of GPT-2 Style language models |
| | 22.06.2026 | |
| Hyperopt | Python library for serial and parallel optimization over awkward search spaces, which may include real-valued, discrete, and conditional dimensions | | | 21.06.2026 | |
| highway-env | A collection of environments for autonomous driving and tactical decision-making tasks | Edouard Leurent |
| | 19.06.2026 |
| SentencePiece | An unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training |
| | 14.06.2026 | |
| RF-DETR | Lightweight, real-time detection transformer that uses weight-sharing neural architecture search to automatically discover optimal accuracy-latency tradeoffs for object detection across diverse target datasets. |
| | | 13.06.2026 |
| Mem0 | Self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users | | | 13.06.2026 | |
| Swarm | Educational framework exploring ergonomic, lightweight multi-agent orchestration | others |
| | 07.06.2026 |
| Duo | This software project implements Duo, a diffusion-based language modeling framework that improves discrete diffusion text generation using Gaussian-guided curriculum learning and Discrete Consistency Distillation for faster training and few-step sampling. | | | 03.06.2026 | |
| Magenta RT | An open-weights live music model that allows you to interactively create, control and perform music in the moment | Chris Donahue | | | 02.06.2026 |
| TorchGeo | PyTorch domain library that provides datasets, transforms, samplers, and pre-trained models specific to geospatial data | | | 01.06.2026 | |
| pymdp | Package for simulating Active Inference agents in Markov Decision Process environments | others | | | 29.05.2026 |
| ActionMesh | Temporal 3D diffusion framework that generates production-ready, topology-consistent animated 3D meshes from inputs like video, text, or static 3D shapes in a fast, feed-forward manner. | | | 28.05.2026 | |
| Lyria 2 | Delivers high-fidelity music and professional-grade audio, capturing subtle nuances across a range of genres and intricate compositions | Katie Nguyen | | 13.05.2026 | |
| Video Seal | Comprehensive framework for neural video watermarking and a competitive open-sourced model |
| | 11.05.2026 | |
| Google Cloud Text-to-Speech | Enables easy integration of Google text recognition technologies into developer applications | | | 07.05.2026 | |
| Imagen 4 | Text-to-image model, with photorealistic images, near real-time speed, and sharper clarity | Katie Nguyen | | 06.05.2026 | |
| CrewAI | Lean, lightning-fast Python framework built entirely from scratch—completely independent of LangChain or other agent frameworks | João Moura | | | 20.04.2026 |
| CodeGemma | How to load, fine-tune and deploy CodeGemma model on SQL by utilising Hugging Face | Carlo Fisicaro | | 20.04.2026 | |
| Hello, many worlds | This tutorial shows how a classical neural network can learn to correct qubit calibration errors | Michael Broughton |
| | 18.04.2026 |
| Text Generation Web UI | The best local UI for large language models, with easy setup and powerful features. 100% offline. | oobabooga | | | 13.04.2026 |
| DataChain | AI-dataframe to enrich, transform and analyze data from cloud storages for ML training and LLM apps | Daniel K | | | 13.04.2026 |
| JAX MD | Differentiable physics and molecular dynamics simulation framework in JAX that enables scalable, GPU-accelerated simulations and end-to-end optimization of entire trajectories, with flexible primitives and neural network integration. | | | 05.04.2026 | |
| GraphCast | Learning skillful medium-range global weather forecasting | | | 30.03.2026 | |
| ignite | High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently. | Anmol Joshi | | | 25.03.2026 |
| edgeai-tensorlab | Edge AI Model Development Tools | Manu |
| | 25.03.2026 |
| Dopamine | Research framework for fast prototyping of reinforcement learning algorithms | | | 24.03.2026 | |
| autoresearch | Bilevel Autoresearch is a bilevel autoresearch framework in which an outer autoresearch loop reads and modifies the code and traces of an inner autoresearch loop to inject new Python search mechanisms at runtime, thereby improving the inner loop’s task search behavior without changing the underlying LLM. | Andrej Karpathy | | | 19.03.2026 |
| Opik | From RAG chatbots to code assistants to complex agentic pipelines and beyond, build LLM systems that run better, faster, and cheaper with tracing, evaluations, and dashboards | Jacques Verré | | | 19.03.2026 |
| PEFT | Parameter-Efficient Fine-Tuning methods enable efficient adaptation of pre-trained language models to various downstream applications without fine-tuning all the model's parameters |
| | 17.03.2026 | |
| tada | Generative text-to-speech and spoken language modeling framework that introduces a one-to-one synchronized text-acoustic tokenization scheme for unified large language model-based speech modeling with reduced hallucinations and inference cost. | | | 16.03.2026 | |
| spiky | This project introduces a spiking neural network paradigm that reframes modern AI models in terms of spike-based polychronization to achieve combinatorially large encoding capacity and dramatically higher energy efficiency than conventional artificial neural networks. | Anatoli S tarostin |
| | 14.03.2026 |
| DeepFloyd IF | State-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding | others |
| | 12.03.2026 |
| Diffusers | Provides pretrained diffusion models across multiple modalities, such as vision and audio, and serves as a modular toolbox for inference and training of diffusion models | Hugging Face |
| | 12.03.2026 |
| CatBoost | High-performance open source library for gradient boosting on decision trees | others | | | 09.03.2026 |
| BEiT | Self-supervised vision representation model, which stands for Bidirectional Encoder representation from Image Transformers |
| | 07.03.2026 | |
| Diffusion_models_tutorial | This project develops diffusion probabilistic models for high-quality image synthesis, leveraging a new connection to denoising score matching with Langevin dynamics to achieve state-of-the-art generative performance and a progressive lossy decompression scheme. | | | 05.03.2026 | |
| HACRL-code | This paper presents Heterogeneous Agent Collaborative Reinforcement Learning, a Reinforcement Learning from Verifiable Reward framework in which heterogeneous agents share verified rollouts during training to collaboratively optimize while still executing independently at inference time. | | | 05.03.2026 | |
| ExecuTorch | PyTorch's unified solution for deploying AI models on-device, from smartphones to microcontrollers, built for privacy, performance, and portability | SaoirseARM | | | 04.03.2026 |
| PaperBanana | Agentic framework that uses advanced vision-language and image-generation models to automatically create and refine publication-ready academic illustrations, evaluated on a new benchmark of methodology diagrams and statistical plots. | | | 03.03.2026 | |
| GigaAgent | Универсальный агент-оркестратор для решения широкого круга задач (ReAct + REPL) | Mikelarg | | | 26.02.2026 |
| Giskard | Open-source library to detect hallucinations and security issues to turn them into test suites that you can automatically execute |
| | 17.02.2026 | |
| SGLang | Fast serving framework for large language models and vision language models | | | 15.02.2026 | |
| Thorsten-Voice | Free to use, offline working, high quality german TTS voice should be available for every project without any license struggling | Thorsten Müller | | | 02.02.2026 |
| fastai | The fastai deep learning library | Sylvain Gugger | | | 28.01.2026 |
| LM Evaluation Harness | Framework for few-shot evaluation of language models. | Lintang Sutawika |
| | 27.01.2026 |
| OpenSpiel | Collection of environments and algorithms for research in general reinforcement learning and search/planning in games | others
| | | 22.01.2026 |
| Keras | Multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO (for inference-only) | François Chollet | | | 21.01.2026 |
| Grounding DINO | Marrying DINO with Grounded Pre-Training for Open-Set Object Detection |
| | 19.01.2026 | |
| GNN | Production-tested library for building GNNs at large scale | others
|
| | 14.01.2026 |
| Gin Config | Lightweight configuration framework for Python, based on dependency injection | | | 14.01.2026 | |
| PyGlove | General-purpose library for Python object manipulation | | | 14.01.2026 | |
| Brax | A differentiable physics engine that simulates environments made up of rigid bodies, joints, and actuators | others | | | 14.01.2026 |
| T5 | Text-To-Text Transfer Transformer | | | 14.01.2026 | |
| SeqIO | Library for processing sequential data to be fed into downstream sequence models | others
|
| | 14.01.2026 |
| TFDS | Collection of ready-to-use datasets for use with TensorFlow, Jax, and other Machine Learning frameworks | Ryan Sepassi |
| | 14.01.2026 |
| TensorFlow Privacy | Library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy |
| | 14.01.2026 | |
| TF-Agents | A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning |
| | 14.01.2026 | |
| Reverb | Efficient and easy-to-use data storage and transport system designed for machine learning research | others |
| | 14.01.2026 |
| ACME | A library of reinforcement learning components and agents |
| | 14.01.2026 | |
| Gemma | Family of open-weights Large Language Model by Google DeepMind, based on Gemini research and technology | | | 14.01.2026 | |
| Sonnet | Library built on top of TensorFlow 2 designed to provide simple, composable abstractions for machine learning research | others
|
Truncated — view the full README on GitHub.
247 followers · starred Oct 2021
26 followers · starred Apr 2023
120 followers · starred May 2023
2,531 followers · starred Oct 2023
