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 |
|---|---|---|---|
| beam-cloud/beta9 Beam (beta9) is an open-source serverless runtime for AI workloads, providing GPU inference endpoints, isolated sandboxes for running untru… | 91 | 1827 | active |
| GestaltCogTeam/BasicTS BasicTS is a Python benchmark library and toolkit for fair and scalable time series analysis, built on PyTorch. It supports forecasting, cl… | 61 | 1826 | active |
| evalplus/evalplus EvalPlus is a Python framework and benchmark suite for rigorously evaluating LLM-synthesized code, providing HumanEval+ and MBPP+ datasets … | 37 | 1826 | active |
| avhz/RustQuant RustQuant is a Rust library for quantitative finance, offering modules for option pricing, stochastic processes, autodiff, statistics, and … | 73 | 1819 | active |
| potamides/DeTikZify DeTikZify is a Python library and research tool that uses multimodal large language models to synthesize TikZ/LaTeX graphics programs from … | 63 | 1819 | active |
| google-research/language A shared repository collecting open-sourced NLP research projects from the Google AI Language team, written in Python. It serves as a home … | 67 | 1816 | active |
| NVIDIA-NeMo/Curator NVIDIA NeMo Curator is a scalable, GPU-accelerated toolkit for preprocessing and curating large text, image, video, and audio datasets for … | 88 | 1814 | active |
| apple/ml-4m 4M is a framework from Apple and EPFL for training any-to-any multimodal foundation models using masked modeling over discrete tokens acros… | 68 | 1814 | active |
| inference-labs-inc/inference-network Inference Network is a Proof of Inference system built on EigenLayer that provides trustless verification of AI inference results via Solid… | 47 | 1814 | active |
| RAVE RAVE is the official PyTorch implementation of a realtime audio variational autoencoder for fast, high-quality neural audio synthesis. It s… | 51 | 1811 | active |
| Overcooked AI A Python library providing clean PyTorch implementations of imitation and reward learning algorithms such as Behavioral Cloning, DAgger, GA… | 23 | 1810 | active |
| Angel Angel is a high-performance distributed parameter server for large-scale machine learning and graph computing, developed by Tencent and Pek… | 66 | 6794 | maintenance |
| supervc-stack/VectorChord VectorChord is a PostgreSQL extension written in Rust for scalable, disk-efficient vector similarity search, serving as the successor to pg… | 73 | 1807 | active |
| worldveil/dejavu Dejavu is a Python library that fingerprints audio files and recognizes songs by matching recorded microphone input or audio from disk agai… | 32 | 6787 | maintenance |
| undertheseanlp/underthesea Underthesea is an open-source Python toolkit for Vietnamese natural language processing that has evolved into an agentic AI toolkit with mu… | 91 | 1806 | active |
| High-Logic/Genie-TTS GENIE is a lightweight Python inference engine for the open-source GPT-SoVITS text-to-speech project, optimized for fast CPU-based speech s… | 58 | 1806 | active |
| thu-ml/RoboticsDiffusionTransformer RDT-1B is a 1B-parameter diffusion foundation model for robot bimanual manipulation, pre-trained on 1M+ multi-robot episodes to predict rob… | 48 | 1806 | active |
| Vitis AI AMD Vitis AI is an integrated development environment and stack for accelerating AI inference on AMD/Xilinx adaptable platforms, including … | 64 | 1805 | active |
| Vchitect/VBench VBench is a comprehensive benchmark suite for evaluating video generative models across hierarchical evaluation dimensions, with prompt sui… | 58 | 1802 | active |
| xhluca/bm25s BM25S is a pure Python library implementing BM25 lexical ranking using Numpy/Scipy sparse matrices with an optional Numba backend, achievin… | 91 | 1800 | active |
| FL33TW00D/whisper-turbo Whisper Turbo is a fast, cross-platform, GPU-accelerated implementation of OpenAI's Whisper speech recognition model, built on the Ratchet … | 19 | 1794 | active |
| lancopku/pkuseg-python pkuseg is a Python toolkit for multi-domain Chinese word segmentation based on the paper by Luo et al. (2019). It provides pre-trained mode… | 23 | 6710 | maintenance |
| 0xSero/turboquant TurboQuant is a Python library implementing near-optimal KV cache quantization for LLM inference, compressing keys to 3-bit and values to 2… | 57 | 1788 | active |
| lehaifeng/T-GCN A collection of research source code implementing Temporal Graph Convolutional Networks (T-GCN) and related variants for urban traffic flow… | 46 | 1787 | active |
| octo-models/octo Octo is an open-source generalist robot policy: a transformer-based diffusion policy pretrained on 800k robot trajectories from the Open X-… | 18 | 1787 | active |
| nsfw-filter/nsfw-filter A free, open-source, privacy-focused browser extension that blocks NSFW images using on-device AI classification with TensorFlow.js. It hid… | 91 | 1786 | active |
| DataArcTech/DataArc-SynData-Toolkit DataArc SynData Toolkit is a Python-based synthetic data generation platform for creating customized LLM training data from local corpora, … | 59 | 1783 | active |
| VAST-AI-Research/UniRig UniRig is the official implementation of a SIGGRAPH 2025 framework that automatically rigs 3D models by predicting skeletons and skinning w… | 55 | 1783 | active |
| Simple-Efficient/RL-Factory RLFactory is a reinforcement learning post-training framework for training agentic LLM models, decoupling the environment from RL training … | 31 | 1783 | active |
| ExtensityAI/symbolicai SymbolicAI is a Python neuro-symbolic framework that blends classical programming with LLM capabilities through composable Symbol primitive… | 93 | 1777 | active |
| CalculatedContent/WeightWatcher WeightWatcher is an open-source Python diagnostic tool for analyzing pre-trained deep neural networks without access to training or test da… | 56 | 1777 | active |
| Farama-Foundation/Minari Minari is a Python library providing a standard format for offline reinforcement learning datasets, with popular reference datasets and uti… | 86 | 1772 | active |
| GAP-LAB-CUHK-SZ/gaustudio GauStudio is a modular PyTorch framework for 3D Gaussian Splatting (3DGS) research and development, supporting novel view synthesis, 3D rec… | 46 | 1763 | active |
| tsurumeso/vocal-remover A Python command-line tool that uses deep neural networks to separate vocals from instrumental tracks in songs. It includes pretrained mode… | 65 | 1761 | stable |
| parthsarthi03/raptor The official Python implementation of RAPTOR (Recursive Abstractive Processing for Tree-Organized Retrieval), a retrieval-augmented generat… | 26 | 1761 | active |
| robocasa/robocasa RoboCasa is a large-scale simulation framework for training and benchmarking generally capable robots on everyday tasks, focused on kitchen… | 78 | 1759 | active |
| AnswerDotAI/ModernBERT ModernBERT is the research repository for a modernized BERT-family bidirectional encoder trained on 2 trillion tokens with an 8192-token co… | 52 | 1758 | active |
| Maximal Update Parametrization (μP) The `mup` Python package implements Maximal Update Parametrization (μP) for PyTorch models, enabling optimal hyperparameters to remain stab… | 10 | 1756 | stable |
| T5 The official T5 library from Google Research, implementing the text-to-text transfer transformer for NLP tasks like summarization, question… | 67 | 6562 | maintenance |
| SamsungSAILMontreal/TinyRecursiveModels Official codebase for the Tiny Recursive Model (TRM) paper, a recursive reasoning approach where a tiny 7M-parameter neural network iterati… | 10 | 6561 | maintenance |
| MaliosDark/wifi-3d-fusion WiFi-3D-Fusion is an open-source research project that estimates 3D human pose from WiFi CSI (Channel State Information) signals using deep… | 22 | 1755 | active |
| datastax/jvector JVector is an embedded approximate nearest neighbor (ANN) search engine for the JVM, implementing a graph index that merges HNSW's hierarch… | 90 | 1754 | active |
| webonnx/wonnx Wonnx is a GPU-accelerated ONNX inference runtime written entirely in Rust, built on wgpu and usable natively or in the browser via WebGPU … | 10 | 1754 | active |
| decisionintelligence/TFB TFB is a comprehensive and fair benchmarking framework for time series forecasting methods, covering deep learning, machine learning, and s… | 70 | 1753 | active |
| facebookresearch/metaseq Metaseq is a PyTorch codebase from Meta AI for training and working with large-scale Open Pre-trained Transformers (OPT), forked from fairs… | 10 | 6544 | maintenance |
| software-mansion/react-native-executorch React Native ExecuTorch is a declarative React Native library for running AI models on-device, powered by Meta's ExecuTorch runtime. It shi… | 88 | 1750 | active |
| Zaneham/Booth Booth is an open-source compiler that takes CUDA C, HIP, or Triton kernel source and emits binaries for AMD RDNA 2/3/4 GPUs, NVIDIA PTX, Te… | 79 | 1750 | active |
| codertimo/BERT-pytorch A PyTorch implementation of Google AI's 2018 BERT model with simple, readable code. It provides CLI tools for building vocabulary and pre-t… | 23 | 6529 | maintenance |
| Informer The official PyTorch implementation of Informer, an efficient Transformer architecture for long sequence time-series forecasting that won t… | 41 | 6528 | maintenance |
| kyleskom/NBA-Machine-Learning-Sports-Betting A Python application that predicts NBA game winners and totals (over/under) using XGBoost and neural network models trained on historical t… | 78 | 1747 | active |
| rusty1s/pytorch_scatter A PyTorch extension library providing highly optimized scatter and segment (sparse update) operations with sum, mean, min, and max reductio… | 57 | 1747 | stable |
| sunny-glow/Auto-BenchMax Auto-BenchMax is a Python pipeline that automatically synthesizes benchmark-targeted training data for LLMs, claiming to more than double a… | 52 | 1745 | active |
| bespokelabsai/curator Bespoke Curator is a Python library for bulk LLM inference and scalable synthetic data curation for post-training and structured data extra… | 89 | 1744 | active |
| google-deepmind/mujoco_mpc MuJoCo MPC (MJPC) is an interactive application and C++ software framework from Google DeepMind for real-time predictive control with the M… | 67 | 1744 | active |
| quantumlib/OpenFermion OpenFermion is an open-source Python library for compiling and analyzing quantum algorithms that simulate fermionic systems, including quan… | 85 | 1741 | active |
| facebookresearch/multimodal TorchMultimodal is a PyTorch library from Meta for training state-of-the-art multimodal multi-task models at scale, covering both content u… | 77 | 1740 | active |
| alkaline-ml/pmdarima pmdarima is a Python statistical library that brings R's auto.arima functionality to Python, wrapping statsmodels ARIMA/SARIMAX models behi… | 81 | 1738 | active |
| MultimediaTechLab/YOLO Official MIT-licensed implementation of the YOLOv9, YOLOv7, and YOLO-RD real-time object detection models, including pre-trained weights, t… | 51 | 1738 | active |
| openai/consistency_models Official PyTorch implementation of Consistency Models, a generative image model family from OpenAI supporting consistency distillation, con… | 10 | 6483 | maintenance |
| google/automl Google Brain's AutoML repository containing implementations of AutoML models and libraries such as EfficientNet, EfficientNetV2, and Effici… | 10 | 6474 | maintenance |
| vdaas/vald Vald is a highly scalable, distributed approximate nearest neighbor (ANN) dense vector search engine built on cloud-native architecture and… | 86 | 1733 | active |
| muscriptor/muscriptor MuScriptor is a multi-instrument music transcription model by Kyutai and Mirelo that converts audio recordings into MIDI and sheet music. I… | 78 | 1732 | active |
| cleverhans-lab/cleverhans CleverHans is a Python library for benchmarking machine learning systems' vulnerability to adversarial examples, providing reference implem… | 23 | 6455 | maintenance |
| jakobrunge/tigramite Tigramite is a Python package for causal inference on time series data, providing causal discovery methods such as PCMCI, PCMCIplus, LPCMCI… | 47 | 1731 | active |
| google-research/circuit_training AlphaChip (circuit_training) is Google's open-source framework for generating chip floorplans using distributed deep reinforcement learning… | 58 | 1730 | active |
| McGill-NLP/llm2vec LLM2Vec is a Python library that converts decoder-only large language models into powerful text encoders via bidirectional attention, maske… | 46 | 1729 | active |
| birdnet-team/BirdNET-Analyzer BirdNET-Analyzer is an open-source Python tool from the Cornell Lab of Ornithology that uses deep learning to identify bird species from au… | 77 | 1728 | active |
| mattpocock/evalite Evalite is a TypeScript-native eval runner for testing LLM-powered applications, built on Vitest with a local dev server UI for exploring o… | 55 | 1724 | active |
| meta-pytorch/tnt TNT (torchtnt) is a lightweight library from Meta providing tools and utilities for PyTorch training workflows. It offers building blocks f… | 77 | 1723 | active |
| facebookresearch/coconut Official PyTorch implementation of Coconut, a method for training large language models to reason in a continuous latent space instead of e… | 58 | 1723 | active |
| gradio-app/trackio Trackio is a lightweight, free, local-first experiment tracking library from Hugging Face that stores metrics in SQLite with an optional Gr… | 82 | 1722 | active |
| Enzyme Enzyme is a high-performance automatic differentiation plugin for LLVM and MLIR that computes derivatives and gradients of arbitrary existi… | 95 | 1718 | active |
| lightly-ai/lightly-train LightlyTrain is a Python framework for training computer vision models, covering pretraining of vision foundation models (DINOv2/v3) on unl… | 83 | 1716 | active |
| sihyun-yu/REPA REPA is the official PyTorch implementation of the ICLR 2025 paper 'Representation Alignment for Generation', a regularization technique th… | 24 | 1716 | active |
| cocodataset/cocoapi Official API for the COCO (Common Objects in Context) dataset, providing Matlab, Python, and Lua interfaces to load, parse, and visualize C… | 32 | 6387 | maintenance |
| kingoflolz/mesh-transformer-jax A JAX/Haiku library implementing model-parallel training and inference of transformer models using xmap/pjit operators, similar to Megatron… | 32 | 6384 | maintenance |
| 4paradigm/OpenMLDB OpenMLDB is an open-source machine learning database that acts as a feature platform, computing consistent features for both offline traini… | 65 | 1714 | active |
| lsdefine/simple_GRPO A minimal (~200 lines) Python implementation of GRPO reinforcement learning for training LLMs to develop r1-like reasoning, built on PyTorc… | 41 | 1714 | active |
| feizc/FluxMusic FluxMusic is the official PyTorch implementation of a rectified flow Transformer model for text-to-music generation, from the paper 'Flux t… | 24 | 1709 | active |
| iMoonLab/yolov13 Official PyTorch implementation of YOLOv13, a real-time object detection model family (Nano to X-Large) featuring Hypergraph-based Adaptive… | 29 | 1708 | active |
| jiaweizzhao/GaLore GaLore is a PyTorch library implementing Gradient Low-Rank Projection for memory-efficient full-parameter training of large language models… | 26 | 1708 | active |
| NuPIC NuPIC is Numenta's open-source machine intelligence platform implementing Hierarchical Temporal Memory (HTM), a computational theory of the… | 23 | 6352 | maintenance |
| whitphx/streamlit-webrtc A Python library that adds real-time video and audio streaming to Streamlit apps via WebRTC. It lets developers process live camera/microph… | 93 | 1707 | active |
| kubeflow/katib Kubeflow Katib is a Kubernetes-native AutoML system for hyperparameter tuning, early stopping, and neural architecture search. It is ML-fra… | 70 | 1706 | stable |
| zai-org/ImageReward ImageReward is the first general-purpose human preference reward model for text-to-image generation, trained on 137k expert comparison pair… | 49 | 1705 | stable |
| xingyaoww/code-act CodeAct is a research framework and agent system that uses executable Python code as a unified action space for LLM agents, enabling multi-… | 27 | 1705 | active |
| airockchip/rknn-llm RKLLM is Rockchip's software stack for converting, quantizing, and running large language models on Rockchip NPU chips such as RK3588 and R… | 83 | 1704 | active |
| BindsNET/bindsnet BindsNET is a Python package for simulating spiking neural networks (SNNs) built on PyTorch tensor functionality, running on CPUs or GPUs. … | 81 | 1704 | active |
| NVlabs/InstantSplat InstantSplat is a research framework for photorealistic 3D scene reconstruction from extremely sparse image views using Gaussian Splatting,… | 30 | 1704 | active |
| DingoDB DingoDB is an open-source distributed multi-modal vector database that combines relational (SQL) and vector semantics in a unified platform… | 66 | 1703 | active |
| PaddlePaddle/PaddleVideo PaddleVideo is a video understanding toolkit built on PaddlePaddle, offering state-of-the-art models for action recognition, temporal actio… | 23 | 1702 | active |
| vllm-project/guidellm GuideLLM is an SLO-aware benchmarking and evaluation platform for LLM inference deployments, simulating real-world workloads against OpenAI… | 92 | 1698 | active |
| scvi-tools scvi-tools is a Python library for deep probabilistic modeling and analysis of single-cell and spatial omics data, built on PyTorch, PyTorc… | 92 | 1697 | stable |
| MLRun MLRun is an open-source MLOps and AI orchestration framework for building, training, deploying, and monitoring machine learning and generat… | 92 | 1697 | active |
| shubham-goel/4D-Humans 4DHumans is a Python research codebase implementing HMR 2.0, a transformer-based model for 3D human mesh recovery from single images, plus … | 56 | 1695 | active |
| stephansturges/WALDO WALDO is an open-source object detection model based on a YOLOv8 backbone, trained with a synthetic data pipeline to detect people, vehicle… | 32 | 1695 | active |
| SciML/ModelingToolkit.jl ModelingToolkit.jl is a Julia-based acausal, equation-based modeling framework and computer algebra system for symbolic-numeric computation… | 95 | 1694 | active |
| tensorly/tensorly TensorLy is a Python library for tensor learning, providing tensor decomposition, tensor algebra, and tensor regression with a simple API. … | 64 | 1693 | stable |
| TensorPack Tensorpack is a high-level neural network training interface built on graph-mode TensorFlow, focused on training speed and flexibility for … | 23 | 6284 | maintenance |
| elixir-nx/axon Axon is a neural network library for Elixir built on top of Nx numerical definitions. It provides a functional API, a high-level model crea… | 89 | 1692 | active |