Open-source machine-learning software
4007 open-source libraries, tools and applications tagged machine-learning, ranked by how closely machine-learning is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
4007 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| awslabs/gluonts GluonTS is a Python library for probabilistic time series modeling, focused on deep learning based forecasting models built on PyTorch. It … | 82 | 5246 | stable |
| wenet-e2e/wenet WeNet is a production-first, end-to-end automatic speech recognition (ASR) toolkit built on PyTorch with transformer/conformer models. It p… | 65 | 5243 | active |
| katanaml/sparrow Sparrow is an open-source framework for structured data extraction from documents (PDFs, images) using ML, LLMs, and Vision LLMs, with sche… | 92 | 5225 | active |
| InternLM/xtuner XTuner is an open-source LLM training engine from InternLM designed for fine-tuning ultra-large-scale Mixture-of-Experts (MoE) models, with… | 68 | 5211 | active |
| Kiln-AI/Kiln Kiln is a free desktop app and MIT-licensed Python library for the full AI development loop: evals, prompt optimization, RAG, agents, fine-… | 91 | 5207 | active |
| lightvector/KataGo KataGo is an open-source Go (baduk) engine trained via AlphaZero-like self-play, one of the strongest Go bots available. It runs as a GTP e… | 95 | 5204 | active |
| Transformer Lab Transformer Lab is an open-source desktop application (built with Electron and Python) that provides a unified GUI for training, fine-tunin… | 82 | 5195 | active |
| hiyouga/EasyR1 EasyR1 is an efficient, scalable reinforcement learning training framework for large language models and vision-language models, built as a… | 62 | 5192 | active |
| h2oai/h2o-llmstudio H2O LLM Studio is a framework and no-code GUI for fine-tuning state-of-the-art large language models, built by H2O.ai. It supports LoRA and… | 96 | 5184 | active |
| grobidOrg/grobid GROBID is a Java machine learning library that extracts, parses, and re-structures raw documents such as PDFs into structured XML/TEI, focu… | 84 | 5176 | active |
| rasbt/mlxtend mlxtend (machine learning extensions) is a Python library of helper tools for day-to-day data science and machine learning tasks. It provid… | 83 | 5176 | active |
| timesler/facenet-pytorch A PyTorch library providing pretrained face detection (MTCNN) and facial recognition (Inception ResNet V1) models, ported from the TensorFl… | 38 | 5169 | stable |
| open-mmlab/mmaction2 MMAction2 is OpenMMLab's PyTorch-based toolbox and benchmark for video understanding, covering action recognition, temporal action localiza… | 52 | 5163 | active |
| facebookresearch/co-tracker CoTracker is a transformer-based model from Meta AI and Oxford VGG that jointly tracks any point (pixel) across a video, handling occlusion… | 57 | 5149 | active |
| ArthurBrussee/brush Brush is a 3D reconstruction engine using Gaussian splatting, built in Rust on the Burn ML framework and WebGPU. It trains and renders spla… | 63 | 5148 | active |
| pytorch/executorch ExecuTorch is PyTorch's framework for exporting and running AI models on-device across mobile, embedded, and edge hardware, with a tiny (~5… | 94 | 5113 | active |
| chatopera/Synonyms A Python library for Chinese synonym lookup and semantic similarity computation, built on word vector models for NLP and chatbot use cases.… | 48 | 5107 | active |
| facebookresearch/AugLy AugLy is a Python data augmentation library from Meta AI supporting audio, image, text, and video with over 100 augmentations. It focuses o… | 66 | 5097 | stable |
| huggingface/text-embeddings-inference Text Embeddings Inference (TEI) is a Rust-based toolkit from Hugging Face for deploying and serving open-source text embedding, re-ranker, … | 93 | 5079 | active |
| Deci-AI/super-gradients SuperGradients is an open-source PyTorch-based training library for building, training, and fine-tuning state-of-the-art computer vision mo… | 50 | 5072 | active |
| microsoft/SPTAG SPTAG is a C++ library from Microsoft for large-scale approximate nearest neighbor (ANN) vector search, offering kd-tree/balanced k-means t… | 77 | 5020 | active |
| Plachtaa/VITS-fast-fine-tuning A Python pipeline for fast fine-tuning of VITS text-to-speech models, enabling speaker adaptation in under an hour from short audio, long a… | 10 | 5009 | active |
| sktime/pytorch-forecasting A PyTorch-based Python library for time series forecasting with state-of-the-art deep learning architectures. It provides a high-level API … | 88 | 4999 | active |
| LangWatch LangWatch is an open-source LLMOps platform for LLM evaluation, AI agent testing, tracing, and production observability. It combines agent … | 91 | 4983 | active |
| going-doer/Paper2Code PaperCoder is a multi-agent LLM system that automatically generates a code repository from a machine learning research paper via a planning… | 49 | 4982 | active |
| shibing624/text2vec A Python library that converts text (words, sentences, paragraphs) into vector embeddings, implementing Word2Vec, RankBM25, BERT, Sentence-… | 49 | 4978 | active |
| apple/embedding-atlas Embedding Atlas is an open-source tool from Apple for interactive visualization of large embeddings and their metadata, supporting clusteri… | 86 | 4969 | active |
| microsoft/muzic Muzic is a Microsoft Research project providing deep learning models for music understanding and generation, including MusicBERT, SongMASS,… | 10 | 4963 | active |
| Picovoice/porcupine Porcupine is a highly-accurate, lightweight on-device wake word detection engine powered by deep neural networks. It enables always-listeni… | 72 | 4959 | stable |
| Nixtla/statsforecast StatsForecast is a Python library providing fast, scalable implementations of statistical and econometric univariate time series forecastin… | 87 | 4938 | stable |
| KaiyangZhou/deep-person-reid Torchreid is a PyTorch library for deep-learning person re-identification, supporting both image and video reid with end-to-end training an… | 47 | 4926 | stable |
| ArrayFire ArrayFire is a general-purpose tensor/numerical computing library for C, C++, and Python that accelerates array operations on GPUs (CUDA, O… | 65 | 4903 | stable |
| google-deepmind/alphageometry Google DeepMind's implementation of AlphaGeometry and DDAR, AI systems that solve Olympiad-level geometry theorem proving problems. It comb… | 52 | 4899 | active |
| zju3dv/EasyMocap EasyMocap is an open-source Python toolbox for markerless human motion capture and novel view synthesis from RGB videos. It fits parametric… | 65 | 4898 | active |
| llm-d llm-d is a Kubernetes-native distributed LLM inference serving stack that orchestrates model servers like vLLM and SGLang across clusters. … | 83 | 4891 | active |
| PaddlePaddle/VisualDL VisualDL is a deep learning visualization toolkit for PaddlePaddle that provides charts for tracking training metrics, visualizing model st… | 23 | 4881 | stable |
| Deep Java Library (DJL) Deep Java Library (DJL) is an engine-agnostic, high-level deep learning framework for Java that supports backends like PyTorch, TensorFlow,… | 96 | 4857 | active |
| cvg/LightGlue LightGlue is a deep neural network library that matches sparse local features across image pairs with high accuracy and fast inference. It … | 47 | 4820 | stable |
| dimforge/nalgebra nalgebra is a general-purpose linear algebra library for Rust providing statically-sized and dynamically-sized vectors and matrices, along … | 76 | 4801 | stable |
| facebookresearch/flow_matching A PyTorch library for implementing flow matching algorithms with continuous, discrete, and Riemannian flow matching implementations. It acc… | 45 | 4801 | active |
| py-why/EconML EconML is a Python package from Microsoft Research's ALICE project for estimating heterogeneous treatment effects from observational data u… | 83 | 4799 | active |
| pytorch/ignite PyTorch-Ignite is a high-level library for training and evaluating neural networks in PyTorch flexibly and transparently. It provides an En… | 84 | 4787 | stable |
| SeldonIO/seldon-core Seldon Core 2 is an MLOps and LLMOps framework for deploying, managing, and scaling machine learning models and modular AI applications on … | 66 | 4782 | active |
| facebookresearch/lingua Meta Lingua is a minimal, fast LLM training and inference library built on easy-to-modify PyTorch components for research purposes. It supp… | 33 | 4771 | active |
| facebookresearch/vjepa2 Official PyTorch codebase and pretrained models for V-JEPA 2, a self-supervised video encoder trained on internet-scale video, plus V-JEPA … | 49 | 4758 | active |
| Rikorose/DeepFilterNet DeepFilterNet is a low-complexity speech enhancement framework that performs real-time noise suppression on full-band 48kHz audio using dee… | 23 | 4757 | active |
| Flux Flux.jl is a machine learning library written entirely in Julia, providing lightweight abstractions over Julia's native GPU support and aut… | 98 | 4754 | stable |
| rust-ml/linfa Linfa is a Rust machine learning framework offering classical ML algorithms and preprocessing, inspired by Python's scikit-learn. It is org… | 76 | 4751 | active |
| esimov/pigo Pigo is a pure Go library for fast face detection, pupil/eye localization, and facial landmark detection based on the Pixel Intensity Compa… | 28 | 4741 | stable |
| deepseek-ai/Engram Official implementation of Engram, a conditional memory module from DeepSeek that modernizes N-gram embeddings for O(1) lookup as a new spa… | 41 | 4735 | active |
| cjlin1/libsvm LIBSVM is a widely used library and command-line toolset for support vector machine classification, regression, and distribution estimation… | 55 | 4715 | stable |
| mindspore-ai/mindspore MindSpore is an open-source deep learning framework for training and inference across mobile, edge, and cloud scenarios. It provides automa… | 32 | 4714 | active |
| google-deepmind/dm_control Google DeepMind's Python stack for physics-based simulation and reinforcement learning environments built on the MuJoCo physics engine. It … | 99 | 4710 | stable |
| mcmonkeyprojects/SwarmUI SwarmUI (formerly StableSwarmUI) is a modular, self-hosted web user interface for AI image generation, supporting models like Stable Diffus… | 70 | 4698 | active |
| OpenNMT/CTranslate2 CTranslate2 is a C++ and Python library for fast, memory-efficient inference of Transformer models on CPU and GPU. It uses quantization, la… | 94 | 4684 | stable |
| PKU-Alignment/align-anything Align-Anything is a modular Python framework for aligning any-to-any (all-modality) large models with human intentions and values using fee… | 45 | 4671 | active |
| makcedward/nlpaug nlpaug is a Python library for augmenting textual, audio, and spectrogram data to improve machine learning model performance. It provides A… | 100 | 4664 | active |
| Blealtan/efficient-kan An efficient pure-PyTorch implementation of Kolmogorov-Arnold Networks (KAN) that reformulates the computation as matrix multiplications ov… | 25 | 4659 | active |
| Tencent/TNN TNN is a high-performance, lightweight deep learning inference framework developed by Tencent Youtu Lab, supporting mobile, desktop, and se… | 28 | 4656 | active |
| facebookresearch/vggt-omega VGGT-Omega is a research library from Oxford VGG and Meta AI providing pretrained transformer models for 3D vision tasks such as camera pos… | 58 | 4644 | active |
| promptslab/Promptify Promptify is a Python library that turns LLMs into task-based NLP engines, providing high-level APIs for NER, classification, QA, and custo… | 62 | 4636 | active |
| joanrod/star-vector StarVector is a foundation model that generates scalable vector graphics (SVG) code from images and text by treating vectorization as a cod… | 46 | 4629 | active |
| hao-ai-lab/FastVideo FastVideo is a unified Python framework for post-training and real-time inference of video diffusion models, covering data preprocessing, f… | 79 | 4616 | active |
| facebook/prophet Prophet is an open‑source library for automatic forecasting of time‑series data with multiple seasonalities. It provides a simple API in Py… | 99 | 20437 | maintenance |
| openxla/xla XLA (Accelerated Linear Algebra) is an open-source machine learning compiler that optimizes models from frameworks like PyTorch, TensorFlow… | 77 | 4605 | active |
| FareedKhan-dev/all-agentic-architectures A Python library packaging 35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, etc.) as runnable Arch… | 58 | 4600 | active |
| real-stanford/diffusion_policy Official PyTorch implementation of Diffusion Policy, a visuomotor robot policy learning method that represents robot behavior as a conditio… | 31 | 4588 | stable |
| RecBole RecBole is a unified, comprehensive and efficient recommendation library built on Python and PyTorch for reproducing and developing recomme… | 23 | 4569 | stable |
| ssrajadh/sentrysearch SentrySearch is a Python CLI tool that provides semantic search over video footage by embedding video chunks with Gemini Embedding, Alibaba… | 64 | 4560 | active |
| lucas-maes/le-wm LeWorldModel (LeWM) is the official PyTorch codebase for a JEPA-based world model that trains stably end-to-end from raw pixels using only … | 49 | 4547 | active |
| NVlabs/tiny-cuda-nn A small, self-contained C++/CUDA framework for training and querying neural networks, featuring a lightning-fast fully fused MLP and a vers… | 66 | 4536 | active |
| OAID/Tengine Tengine is a lightweight, high-performance, modular deep learning inference engine developed by OPEN AI LAB for embedded and edge devices. … | 23 | 4531 | active |
| dedupe Dedupe is a Python library that uses machine learning to perform fuzzy matching, deduplication, and entity resolution on structured data. I… | 44 | 4516 | stable |
| modelscope/ClearerVoice-Studio ClearerVoice-Studio is an open-source, AI-powered speech processing toolkit from ModelScope/Alibaba offering state-of-the-art pretrained mo… | 35 | 4515 | active |
| salesforce/Merlion Merlion is a Python library from Salesforce providing an end-to-end machine learning framework for time series intelligence, covering forec… | 10 | 4486 | active |
| zjunlp/DeepKE DeepKE is an open-source PyTorch-based knowledge extraction toolkit for knowledge graph construction, supporting named entity recognition, … | 61 | 4484 | active |
| unionai-oss/pandera Pandera is a Python library for statistical data validation of dataframe-like objects, supporting pandas, polars, PySpark, and others. It l… | 99 | 4481 | stable |
| Mobile ALOHA Mobile ALOHA is an open-source system for low-cost whole-body teleoperation and data collection with a bimanual mobile manipulation robot, … | 29 | 4478 | active |
| DeepXDE DeepXDE is a Python library for scientific machine learning and physics-informed learning, built on top of PyTorch, TensorFlow, JAX, and Pa… | 74 | 4477 | stable |
| rom1504/img2dataset A Python tool that downloads large sets of image URLs and packages them into machine learning datasets, with resizing and caption support. … | 52 | 4454 | active |
| EvolvingLMMs-Lab/lmms-eval lmms-eval is a unified Python framework for evaluating large multimodal models across text, image, video, and audio tasks, with 100+ benchm… | 87 | 4453 | active |
| layumi/Person_reID_baseline_pytorch A small, friendly PyTorch baseline implementation for person and vehicle re-identification (ReID). It reproduces strong top-conference resu… | 67 | 4450 | stable |
| mosaicml/llm-foundry LLM Foundry is a PyTorch-based codebase for training, finetuning, evaluating, and deploying large language models from 125M to 70B+ paramet… | 61 | 4449 | active |
| xlite-dev/lite.ai.toolkit A lightweight C++ toolkit providing unified APIs for 100+ pre-trained AI models across inference backends like ONNX Runtime, MNN, TensorRT,… | 72 | 4439 | active |
| tensorflow/probability TensorFlow Probability is a Python library for probabilistic reasoning and statistical analysis built on TensorFlow, with a JAX substrate. … | 66 | 4435 | active |
| onnxsim/onnxsim ONNX Simplifier (onnxsim) is a tool that simplifies ONNX models by inferring the whole computation graph and replacing redundant operators … | 99 | 4415 | active |
| microsoft/FLAML FLAML is a lightweight Python library for automated machine learning (AutoML) and hyperparameter tuning. It efficiently finds quality model… | 94 | 4414 | active |
| open-compass/VLMEvalKit VLMEvalKit is an open-source Python toolkit for evaluating large vision-language models (LMMs/LVLMs) across 80+ benchmarks with support for… | 61 | 4412 | active |
| HIP HIP is a C++ runtime API and kernel programming language for AMD GPUs that mirrors the NVIDIA CUDA programming interface. It enables develo… | 90 | 4406 | active |
| DistrictDataLabs/yellowbrick Yellowbrick is a Python library of visual diagnostic tools called Visualizers that extend the scikit-learn API using matplotlib. It helps u… | 23 | 4405 | active |
| iperov/DeepFaceLab DeepFaceLab is the leading open-source Windows application for creating deepfakes, allowing users to swap, de-age, or replace faces and hea… | 10 | 19274 | maintenance |
| limix-ldm-ai/LimiX LimiX is the first large structured-data foundation model (LDM), a transformer-based model for tabular data that handles classification, re… | 61 | 4387 | active |
| AI4Finance-Foundation/ElegantRL ElegantRL is a lightweight, modular deep reinforcement learning library built on PyTorch that implements core model-free RL algorithms (PPO… | 50 | 4368 | active |
| rust-ndarray/ndarray ndarray is a Rust crate providing an n-dimensional array container for general elements and numerics, with owned arrays, lightweight array … | 85 | 4330 | active |
| unum-cloud/USearch USearch is a fast, single-file similarity search and clustering engine for vectors and arbitrary objects, supporting spatial, binary, proba… | 89 | 4325 | active |
| umlx5h/LLPlayer LLPlayer is a Windows media player built for language learning, featuring dual subtitles, AI-generated subtitles via Whisper ASR, real-time… | 76 | 4325 | active |
| ymcui/Chinese-LLaMA-Alpaca A project releasing Chinese-adapted LLaMA and instruction-tuned Alpaca large language models with extended Chinese vocabulary, plus pre-tra… | 53 | 18936 | maintenance |
| tloen/alpaca-lora A repository of scripts for reproducing Stanford Alpaca-style instruction tuning of LLaMA models using low-rank adaptation (LoRA) on consum… | 31 | 18899 | maintenance |
| NeuralProphet NeuralProphet is a Python library for interpretable time series forecasting built on PyTorch, combining neural networks with traditional ti… | 23 | 4301 | active |
| Nixtla/neuralforecast NeuralForecast is a Python library offering a large collection of state-of-the-art neural forecasting models (NBEATS, NHITS, TFT, PatchTST,… | 97 | 4277 | active |