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 |
|---|---|---|---|
| txtai txtai is an all-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows, built around an embedd… | 95 | 12978 | active |
| PaddlePaddle/PaddleNLP PaddleNLP is an easy-to-use NLP and large language model development kit built on the PaddlePaddle deep learning framework, with a large pr… | 59 | 12977 | active |
| Vision Transformer Google Research's official JAX/Flax implementation of Vision Transformer (ViT) and MLP-Mixer architectures, with released pretrained checkp… | 76 | 12744 | stable |
| PaddleSpeech PaddleSpeech is an open-source speech and audio toolkit built on the PaddlePaddle deep learning platform, covering ASR with punctuation, st… | 63 | 12689 | active |
| Farama-Foundation/Gymnasium Gymnasium is a Python library providing a standard API for single-agent reinforcement learning environments, maintained by the Farama Found… | 95 | 12663 | stable |
| bmaltais/kohya_ss A Gradio-based GUI and CLI wrapper around Kohya's Stable Diffusion training scripts for fine-tuning diffusion image generation models. It s… | 89 | 12616 | active |
| axolotl-ai-cloud/axolotl Axolotl is a free, open-source, config-driven framework for fine-tuning large language models, supporting SFT, preference learning (DPO/KTO… | 98 | 12591 | active |
| BentoML OpenLLM is a Python framework and CLI for self-hosting open-source large language models (Llama, DeepSeek, Qwen, Mistral, etc.) as OpenAI-c… | 76 | 12552 | active |
| cupy/cupy CuPy is a NumPy/SciPy-compatible array library for GPU-accelerated computing with Python, running on NVIDIA CUDA or AMD ROCm. It acts as a … | 92 | 12362 | stable |
| FlagOpen/FlagEmbedding FlagEmbedding is the official Python toolkit for BAAI's BGE family of embedding models and rerankers, covering inference, evaluation, and f… | 82 | 12242 | active |
| xmu-xiaoma666/External-Attention-pytorch A PyTorch library (fightingcv-attention) providing clean, minimal implementations of numerous attention mechanisms, MLP variants, re-parame… | 61 | 12186 | active |
| Autoware Autoware is the world's leading open-source, production-ready software stack for autonomous driving, built on ROS 2 and hosted by the Autow… | 90 | 12155 | stable |
| LMCache/LMCache LMCache is a KV cache management layer for LLM inference that stores, compresses, and reuses KV caches across requests, sessions, and servi… | 88 | 12133 | active |
| google/sentencepiece SentencePiece is a fast, lightweight unsupervised text tokenizer and detokenizer for neural network-based text generation systems, implemen… | 83 | 12132 | stable |
| ostris/ai-toolkit An all-in-one open-source training toolkit for finetuning diffusion models (image and video) on consumer-grade hardware. It supports many r… | 72 | 12107 | active |
| nerfstudio Nerfstudio is a Python library and CLI toolkit providing a simple, modular API for creating, training, and testing Neural Radiance Fields (… | 34 | 12019 | active |
| facebookresearch/sam3 Official code for Meta's Segment Anything Model 3 (SAM 3), a unified foundation model for promptable segmentation in images and videos. It … | 63 | 11957 | active |
| NVIDIA/cosmos NVIDIA Cosmos is an open platform of omnimodal world foundation models, datasets, and tools for building Physical AI systems such as robots… | 69 | 11892 | active |
| facebookresearch/seamless_communication A library of foundational multilingual multimodal AI models from Meta for speech and text translation, including SeamlessM4T, SeamlessExpre… | 71 | 11889 | active |
| SpeechBrain SpeechBrain is an open-source PyTorch-based speech toolkit for building conversational AI systems. It provides training recipes, pretrained… | 85 | 11845 | active |
| ludwig-ai/ludwig Ludwig is a declarative, low-code deep learning framework for training, fine-tuning, and deploying AI models — from LLMs to tabular, image,… | 96 | 11775 | active |
| qubvel-org/segmentation_models.pytorch A PyTorch library providing neural networks for image semantic segmentation with a simple high-level API. It includes 12 encoder-decoder ar… | 68 | 11745 | stable |
| tensorzero/tensorzero TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation behi… | 10 | 11716 | active |
| LanceDB LanceDB is an open-source embedded vector database and multimodal AI lakehouse built on the Lance columnar format, written in Rust with Pyt… | 94 | 11706 | active |
| cleanlab Cleanlab is a Python library for data-centric AI that automatically detects issues in ML datasets, such as label errors, outliers, duplicat… | 56 | 11692 | stable |
| CorentinJ/Real-Time-Voice-Cloning A Python implementation of the SV2TTS (Transfer Learning from Speaker Verification to Multispeaker TTS) framework that clones a voice from … | 61 | 60174 | maintenance |
| facebookresearch/dinov3 Reference PyTorch implementation and pretrained models for DINOv3, Meta's self-supervised vision transformer backbone family. It includes t… | 56 | 11536 | active |
| rerun-io/rerun Rerun is an open-source SDK and viewer for logging, storing, querying, and visualizing multi-rate multimodal data such as images, point clo… | 96 | 11498 | active |
| THU-MIG/yolov10 YOLOv10 is a real-time end-to-end object detection model family that removes NMS post-processing via consistent dual assignments and optimi… | 17 | 11331 | active |
| Weights & Biases Weights & Biases (wandb) is a Python SDK and platform for tracking, visualizing, and managing machine learning experiments, including metri… | 100 | 11303 | active |
| FiftyOne FiftyOne is an open-source Python library and GUI app for building high-quality computer vision datasets and models. It enables visualizing… | 98 | 11184 | active |
| huggingface/tokenizers Hugging Face Tokenizers is a fast, Rust-based library implementing state-of-the-art tokenization algorithms (BPE, WordPiece, Unigram) with … | 95 | 11181 | stable |
| huggingface/skills A collection of Agent Skills (SKILL.md folders) that teach AI coding agents how to use the Hugging Face ecosystem, including the hf-cli ski… | 61 | 11176 | active |
| Numba Numba is an open-source NumPy-aware JIT compiler that translates a subset of Python and NumPy code into fast machine code using LLVM. It su… | 94 | 11175 | stable |
| pathwaycom/arc-task-gen A Python tool that generates original ARC-AGI-1-style puzzle tasks distribution-matched to the public evaluation set. It produces tasks in … | 53 | 11149 | active |
| WhisperLiveKit WhisperLiveKit is a self-hosted, ultra-low-latency real-time speech-to-text pipeline built on state-of-the-art simultaneous speech research… | 85 | 11096 | active |
| Triton Inference Server NVIDIA Triton Inference Server is an open-source inference serving software that deploys AI models from multiple frameworks (TensorRT, PyTo… | 98 | 11075 | stable |
| Kedro Kedro is an open-source Python framework for building production-ready data engineering and data science pipelines using software engineeri… | 95 | 11028 | stable |
| thu-ml/tianshou Tianshou is a modular, high-performance deep reinforcement learning library built on pure PyTorch and Gymnasium. It offers both low-level h… | 66 | 11000 | active |
| OpenVINO OpenVINO is an open-source toolkit from Intel for optimizing and deploying deep learning inference across CPU, GPU, and NPU hardware. It su… | 95 | 10996 | stable |
| face_recognition A Python library and command-line tool providing a simple API for face detection, facial landmark extraction, and face recognition, built o… | 59 | 56796 | maintenance |
| google/dopamine Dopamine is a research framework from Google for fast prototyping of reinforcement learning algorithms, built around a small, easily readab… | 52 | 10925 | active |
| Natural Natural is a general natural language processing library for Node.js offering tokenizing, stemming, part-of-speech tagging, sentiment analy… | 58 | 10881 | active |
| karpathy/minbpe A minimal, clean Python implementation of the byte-level Byte Pair Encoding (BPE) algorithm used for tokenization in modern LLMs like GPT-4… | 26 | 10830 | stable |
| OpenPipe/ART ART (Agent Reinforcement Trainer) is an open-source Python framework for training multi-step LLM agents using reinforcement learning techni… | 85 | 10813 | active |
| huggingface/ml-intern An open-source autonomous ML engineer agent from Hugging Face that reads papers, writes code, trains models, and ships ML work using the Hu… | 10 | 10810 | active |
| doccano Doccano is an open-source, web-based text annotation tool for building labeled datasets for machine learning. It supports text classificati… | 60 | 10794 | active |
| autogluon/autogluon AutoGluon is an AutoML library that automates machine learning on tabular data, time series, text, and images with just a few lines of Pyth… | 93 | 10766 | active |
| SkyPilot SkyPilot is an open-source AI compute platform that unifies fragmented infrastructure (Kubernetes, Slurm, VMs, 20+ clouds) into a single po… | 100 | 10724 | active |
| hydra-ecosystem/hydra Hydra is a Python framework for elegantly configuring complex applications through dynamic, hierarchical configuration composition. It allo… | 100 | 10710 | stable |
| lucidrains/denoising-diffusion-pytorch A PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) for generative image modeling, published on PyPI as denoising_d… | 86 | 10707 | active |
| Baiyuetribe/paper2gui Paper2GUI (now branded 小白兔AI / Xiaobaitu AI) is a desktop AI toolbox application that packages 50+ AI research models into install-free GUI… | 23 | 10699 | active |
| IDEA-Research/GroundingDINO Official PyTorch implementation of Grounding DINO, an open-set object detector that fuses a Transformer-based DINO detector with grounded v… | 22 | 10682 | stable |
| X-AnyLabeling X-AnyLabeling is a cross-platform desktop application for AI-assisted annotation of text, image, video, and multimodal data. It bundles bui… | 96 | 10642 | active |
| abetlen/llama-cpp-python Python bindings for llama.cpp providing low-level ctypes access to the C API plus a high-level API for text completion with OpenAI-like int… | 92 | 10638 | active |
| Megvii-BaseDetection/YOLOX YOLOX is a high-performance anchor-free YOLO object detection model family implemented in PyTorch, with pretrained weights and export suppo… | 30 | 10628 | stable |
| bigscience-workshop/petals Petals is a Python library that lets you run and fine-tune large language models (Llama 3.1, Mixtral, Falcon, BLOOM) on a BitTorrent-style … | 23 | 10614 | active |
| pyannote.audio pyannote.audio is an open-source Python toolkit built on PyTorch for speaker diarization, providing neural building blocks like voice activ… | 92 | 10593 | active |
| NVIDIA/cutlass CUTLASS is NVIDIA's collection of CUDA C++ template abstractions and Python DSLs for implementing high-performance GEMM and related linear … | 98 | 10580 | active |
| facebookresearch/xformers xFormers is a PyTorch-based library of hackable, optimized Transformer building blocks with custom CUDA kernels for fast, memory-efficient … | 87 | 10565 | active |
| vwxyzjn/cleanrl CleanRL is a deep reinforcement learning library providing high-quality, single-file implementations of algorithms like PPO, DQN, DDPG, TD3… | 54 | 10481 | active |
| FreeMoCap FreeMoCap is a free, open-source, markerless motion capture system that uses ordinary cameras (webcams, GoPros, smartphones) to record and … | 98 | 10437 | active |
| fossasia/visdom Visdom is a Python tool for real-time visualization, monitoring, and collaborative analysis of live data and ML experiments. It provides a … | 87 | 10322 | active |
| snakers4/silero-vad Silero VAD is a pre-trained, enterprise-grade Voice Activity Detector model available via PyPI, runnable with PyTorch or ONNX Runtime. It d… | 93 | 10317 | stable |
| open-mmlab/Amphion Amphion is an open-source Python toolkit for audio, music, and speech generation, supporting tasks like text-to-speech, voice conversion, s… | 48 | 10304 | active |
| Metaflow Metaflow is a human-centric Python framework from Netflix for building, managing, and deploying real-life AI/ML and data science systems. I… | 92 | 10280 | stable |
| deepseek-ai/DeepEP DeepEP is a high-performance GPU communication library for expert parallelism (EP) in MoE training and inference, providing high-throughput… | 55 | 10263 | active |
| Moondream Moondream is an open-weight family of small, efficient vision language models (2B to 9B MoE) that perform image captioning, visual question… | 58 | 10127 | active |
| stanfordnlp/CoreNLP Stanford CoreNLP is a Java suite of natural language processing tools that annotates raw text with tokenization, POS tags, named entities, … | 89 | 10122 | stable |
| drivendataorg/cookiecutter-data-science Cookiecutter Data Science (CCDS) is a Python CLI tool that scaffolds standardized, flexible data science project structures with best pract… | 78 | 10086 | active |
| sktime sktime is a unified Python framework for machine learning with time series, offering 500+ models behind a single scikit-learn-compatible AP… | 98 | 10062 | stable |
| TPOT TPOT (Tree-based Pipeline Optimization Tool) is a Python automated machine learning library that optimizes scikit-learn machine learning pi… | 40 | 10053 | active |
| OpenRLHF/OpenRLHF OpenRLHF is a high-performance, production-ready open-source RLHF framework built on Ray + vLLM + DeepSpeed for scalable reinforcement lear… | 89 | 10040 | active |
| OpenMined/PySyft PySyft is a Python library that lets data scientists run computations on private data that stays on the data owner's server, with results s… | 73 | 10034 | active |
| yzhao062/pyod PyOD is the most comprehensive Python library for anomaly detection, offering 60+ detectors across tabular, time series, graph, text, image… | 96 | 10026 | stable |
| opendatalab/PDF-Extract-Kit PDF-Extract-Kit is a Python model toolbox for high-quality PDF content extraction, integrating state-of-the-art models for layout detection… | 15 | 10023 | active |
| ESPnet ESPnet is an end-to-end speech processing toolkit built on PyTorch covering speech recognition, text-to-speech, speech translation, enhance… | 94 | 9989 | active |
| kyutai-labs/pocket-tts Pocket TTS is a lightweight 100M-parameter text-to-speech model and Python library from Kyutai that runs efficiently on CPUs without a GPU.… | 83 | 9923 | active |
| huggingface/accelerate Hugging Face Accelerate is a Python library that lets you run the same PyTorch training and inference code on any device or distributed con… | 94 | 9916 | stable |
| gorse-io/gorse Gorse is an AI-powered open-source recommender system engine written in Go that ingests items, users, and interaction feedback and automati… | 95 | 9876 | active |
| PyCaret PyCaret is an open-source, low-code AutoML library for Python that wraps scikit-learn to automate training, tuning, and comparison of model… | 79 | 9846 | active |
| Tiiny-AI/PowerInfer PowerInfer is a CPU/GPU hybrid LLM inference engine that exploits activation locality to run large language models fast on consumer-grade h… | 60 | 9814 | active |
| PyMC PyMC is a Python library for Bayesian statistical modeling and probabilistic programming, built on PyTensor. It provides intuitive model sp… | 96 | 9774 | stable |
| roboflow/rf-detr RF-DETR is a real-time transformer-based model architecture from Roboflow for object detection, instance segmentation, and keypoint detecti… | 86 | 9678 | active |
| xorbitsai/inference Xinference is an open-source model serving platform for deploying LLMs, embedding, speech, image, and multimodal models via a unified OpenA… | 93 | 9616 | active |
| arogozhnikov/einops einops is a Python library providing readable, framework-agnostic tensor operations via mini-language functions like rearrange, reduce, and… | 71 | 9615 | stable |
| WongKinYiu/yolov9 Official PyTorch implementation of the YOLOv9 object detection paper, featuring Programmable Gradient Information for improved accuracy. It… | 17 | 9562 | active |
| Spring AI Spring AI is an application framework for AI engineering that provides Spring-friendly, portable abstractions for integrating AI models int… | 94 | 9542 | active |
| unit8co/darts Darts is a Python library for user-friendly time series forecasting and anomaly detection. It provides a unified scikit-learn-like fit/pred… | 92 | 9533 | active |
| PeterL1n/RobustVideoMatting Robust Video Matting (RVM) is a deep learning model and library for real-time human video matting, using a recurrent neural network with te… | 23 | 9533 | stable |
| MakazhanAlpamys/Soup Soup is a Python CLI that fine-tunes and post-trains LLMs from a single YAML config, supporting 23 methods (SFT, DPO, ORPO, SimPO, KTO, etc… | 79 | 9486 | active |
| Cog Cog is an open-source CLI tool that packages machine learning models into production-ready Docker containers using a simple cog.yaml config… | 97 | 9484 | active |
| blue-yonder/tsfresh tsfresh is a Python package that automatically extracts hundreds of features from time series using algorithms from statistics, signal proc… | 74 | 9470 | stable |
| OneFlow OneFlow is an open-source deep learning framework written in C++ with a PyTorch-like Python API, focused on scalable and efficient distribu… | 44 | 9437 | active |
| oumi-ai/oumi Oumi is an open-source Python framework and platform for the end-to-end lifecycle of open-weight LLMs: data synthesis, fine-tuning (SFT, Lo… | 91 | 9407 | active |
| PaddlePaddle/PaddleSeg PaddleSeg is an end-to-end image segmentation toolkit built on PaddlePaddle, offering a model zoo with dozens of pre-trained models for sem… | 49 | 9395 | active |
| QwenAudio/SenseVoice SenseVoice is an open-source speech foundation model (SenseVoiceSmall) providing multilingual ASR, spoken language identification, speech e… | 87 | 9386 | active |
| ML.NET ML.NET is an open-source, cross-platform machine learning framework for .NET that lets developers build, train, and deploy custom ML models… | 78 | 9356 | active |
| keras-team/autokeras AutoKeras is an AutoML library for deep learning built on Keras, developed by DATA Lab at Texas A&M University. It automates model architec… | 46 | 9336 | active |
| bytedance/monolith Monolith is a deep learning framework built on TensorFlow for large-scale recommendation modeling. It provides collisionless embedding tabl… | 10 | 9286 | active |