Open-source machine-learning software
5374 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.
5374 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| LLaVA-VL/LLaVA-NeXT LLaVA-NeXT is a collection of open large multimodal models (LLaVA-NeXT, LLaVA-Video, LLaVA-OneVision, LLaVA-Critic-R1) that combine vision … | 61 | 4729 | maintenance |
| Vahe1994/AQLM Official PyTorch implementation of AQLM, an extreme LLM compression method via additive quantization, extended with PV-Tuning for finetunin… | 54 | 1329 | active |
| apple/python-apple-fm-sdk Python bindings for Apple's Foundation Models framework, giving access to the on-device foundation model behind Apple Intelligence on macOS… | 76 | 1327 | active |
| PrunaAI/pruna Pruna is an open-source Python model optimization framework that makes AI models faster, smaller, cheaper, and greener via caching, quantiz… | 82 | 1326 | active |
| Tongjilibo/bert4torch bert4torch is a PyTorch library providing an elegant reimplementation of transformer models (BERT, RoBERTa, T5, GPT, ChatGLM, LLaMA, etc.) … | 76 | 1326 | active |
| agemagician/ProtTrans ProtTrans provides state-of-the-art pre-trained Transformer language models for protein sequences, trained on thousands of GPUs and hundred… | 29 | 1326 | active |
| jishengpeng/WavTokenizer WavTokenizer is a state-of-the-art discrete neural audio codec that compresses speech, music, and general audio into only 40 or 75 discrete… | 23 | 1325 | active |
| inference-labs-inc/JSTprove JSTprove is a Rust CLI toolkit that generates zero-knowledge proofs of machine learning inference on ONNX models, built on Polyhedra Networ… | 64 | 1324 | active |
| Duxiaoman-DI/XuanYuan XuanYuan is a family of open-source Chinese financial-domain large language models from Duxiaoman, including base, chat, and quantized vari… | 30 | 1324 | active |
| tensorflow/lucid Lucid is a collection of infrastructure and tools for research in neural network interpretability, built on TensorFlow 1.x. It provides fea… | 10 | 4704 | maintenance |
| sjtuytc/UnboundedNeRFPytorch A PyTorch implementation benchmarking state-of-the-art unbounded (large-scale) neural radiance field methods like NeRF++, DVGO, and Block-N… | 23 | 1323 | active |
| DBraun/DawDreamer DawDreamer is a Python framework that provides digital audio workstation features, letting users compose graphs of audio processors includi… | 84 | 1322 | active |
| yeyupiaoling/VoiceprintRecognition-Pytorch A PyTorch-based voiceprint recognition (speaker recognition) framework implementing models such as ECAPA-TDNN, ResNetSE, ERes2Net, and CAM+… | 75 | 1322 | active |
| ImprintLab/Medical-SAM-Adapter Medical SAM Adapter (MSA) is a Python framework that fine-tunes Meta's Segment Anything Model for medical image segmentation using lightwei… | 35 | 1322 | active |
| sebp/scikit-survival scikit-survival is a Python library for survival analysis (time-to-event modeling) built on top of scikit-learn. It provides survival model… | 84 | 1321 | active |
| meta-pytorch/segment-anything-fast A fast, batched offline inference-oriented fork of Meta's Segment Anything (SAM) image segmentation model. It applies optimizations like bf… | 42 | 1321 | active |
| stared/livelossplot A Python library that draws live training loss and metric plots inside Jupyter Notebooks for Keras, PyTorch, and other deep learning framew… | 85 | 1320 | stable |
| kwai/DouZero DouZero is a deep reinforcement learning framework that masters the Chinese card game DouDizhu through self-play, published at ICML 2021 by… | 23 | 4685 | maintenance |
| sanchit-gandhi/whisper-jax An optimized JAX implementation of OpenAI's Whisper speech recognition model, built on Hugging Face Transformers, offering up to 70x faster… | 31 | 4680 | maintenance |
| ChenmienTan/RL2 RL2 (Ray Less Reinforcement Learning) is a concise Python library for post-training large language models with reinforcement learning, SFT,… | 54 | 1316 | active |
| sicara/easy-few-shot-learning A Python library (easyfsl) with ready-to-use code and tutorial notebooks for few-shot image classification and meta-learning, built on PyTo… | 23 | 1316 | stable |
| General Navigation Models Official code and pre-trained checkpoints for the GNM, ViNT, and NoMaD family of general-purpose goal-conditioned visual navigation policie… | 20 | 1315 | active |
| arkflow-rs/arkflow ArkFlow is a high-performance stream processing engine written in Rust on top of Tokio, connecting configurable inputs (Kafka, MQTT, HTTP, … | 88 | 1314 | active |
| Alibaba-NLP/ZeroSearch ZeroSearch is a reinforcement learning framework from Alibaba's Tongyi Lab that trains LLMs to use search by simulating search engine resul… | 32 | 1313 | active |
| OpenTeleVision/TeleVision Open-TeleVision is an open-source immersive robot teleoperation system that streams stereoscopic visual feedback to VR headsets (Apple Visi… | 25 | 1313 | active |
| Albert-Weasker/niubi_guard An open-source defense system that protects GitHub repositories from spam, harassment, and coordinated abuse via configurable detection sig… | 59 | 1312 | active |
| deepseek-ai/DeepSeek-Prover-V2 DeepSeek-Prover-V2 is an open-source large language model for formal theorem proving in Lean 4, trained via reinforcement learning with sub… | 31 | 1311 | active |
| vye16/shape-of-motion Shape of Motion is a Python research codebase for 4D reconstruction of dynamic scenes from a single monocular video, based on the ICCV 2025… | 27 | 1311 | active |
| Parskatt/RoMa RoMa (romatch) is a Python library for robust dense feature matching between image pairs, estimating pixel-dense warps and reliable certain… | 46 | 1309 | active |
| donydchen/mvsplat MVSplat is a PyTorch implementation of an ECCV 2024 Oral model that predicts 3D Gaussians from sparse multi-view images in a single feed-fo… | 58 | 1308 | active |
| openai/simple-evals A lightweight Python library from OpenAI for evaluating language models against benchmarks like MMLU, GPQA, MATH, HumanEval, SimpleQA, Heal… | 57 | 4638 | maintenance |
| seetaface/SeetaFaceEngine SeetaFace Engine is an open-source C++ face recognition engine comprising face detection, face alignment, and face identification modules. … | 32 | 4638 | maintenance |
| SakanaAI/text-to-lora Text-to-LoRA (T2L) is a hypernetwork that generates LoRA adapters for large language models in a single forward pass, using only a natural … | 28 | 1307 | active |
| albermax/innvestigate iNNvestigate is a Python toolbox providing a common interface and out-of-the-box implementations of many neural network explanation methods… | 26 | 1307 | active |
| Vincentqyw/image-matching-webui A Gradio-based web UI that matches keypoints between two images using many state-of-the-art image matching algorithms (LoFTR, SuperGlue, Li… | 85 | 1306 | active |
| huawei-noah/Efficient-Computing A collection of efficient deep learning methods from Huawei Noah's Ark Lab, covering model compression, knowledge distillation, pruning, qu… | 32 | 1306 | active |
| ali-vilab/MimicBrush MimicBrush is the official implementation of a zero-shot image editing method that lets users mask a region in a source image and provide a… | 25 | 1306 | active |
| DAMO-NLP-SG/VideoLLaMA2 VideoLLaMA 2 is an open-source video large language model that adds spatial-temporal modeling and audio understanding to video-LLMs. It pro… | 25 | 1306 | active |
| turboderp-org/exllamav2 ExLlamaV2 is a fast Python inference library for running large language models locally on modern consumer GPUs, with support for EXL2/GPTQ … | 58 | 4631 | maintenance |
| derrian-distro/LoRA_Easy_Training_Scripts A PySide6 desktop GUI that wraps Kohya's sd-scripts to simplify training LoRA, LoCon, and other LoRA-type models for Stable Diffusion. It s… | 30 | 1304 | active |
| bambinos/bambi Bambi is a high-level Bayesian model-building interface for Python built on top of the PyMC probabilistic programming framework. It uses a … | 93 | 1303 | active |
| okfn-brasil/serenata-de-amor Operação Serenata de Amor is an open-source data science project that uses machine learning to audit Brazilian congresspeople's public expe… | 32 | 4612 | maintenance |
| InternRobotics/InternUtopia InternUtopia (formerly GRUtopia) is a Python simulation platform built on NVIDIA Isaac Sim for embodied AI research, supporting diverse rob… | 36 | 1301 | active |
| luosiallen/latent-consistency-model Official implementation of Latent Consistency Models (LCM), a diffusion-based approach for synthesizing high-resolution images with few-ste… | 28 | 4607 | maintenance |
| buoyancy99/diffusion-forcing Official research code for the NeurIPS paper 'Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion', implementing a metho… | 61 | 1299 | active |
| STVIR/pysot PySOT is a Python research platform by SenseTime for single object visual tracking, implementing algorithms such as SiamRPN, SiamRPN++, DaS… | 41 | 4602 | maintenance |
| W2GenAI-Lab/LucidFlux LucidFlux is a caption-free photo-realistic image restoration model built on a large-scale diffusion transformer, released with inference a… | 52 | 1298 | active |
| jbarrow/commonforms CommonForms is a Python package and CLI that uses trained object-detection models (FFDNet-S/L) to automatically detect form fields in a PDF… | 59 | 1297 | active |
| thu-ml/Motus Motus is the official implementation of a unified latent action world model for robotics, combining a video generation model, a vision-lang… | 40 | 1297 | active |
| PantoMatrix/PantoMatrix PantoMatrix is an open-source research project that generates 3D face and body animation from speech audio, including the EMAGE model for h… | 32 | 1297 | active |
| ZhengyiLuo/PHC Official implementation of the ICCV 2023 paper 'Perpetual Humanoid Control for Real-time Simulated Avatars'. It provides a Python codebase … | 41 | 1296 | active |
| AnyStyle AnyStyle is a fast machine-learning-based parser that splits bibliographic references into structured segments like author, title, and publ… | 38 | 1295 | active |
| MV-Adapter MV-Adapter is a plug-and-play adapter that turns pre-trained text-to-image diffusion models (e.g., SDXL, SD2.1) into multi-view consistent … | 31 | 1295 | active |
| Inpaint Anything A Stable Diffusion Web UI extension that performs inpainting and outpainting using masks generated by Segment Anything models (SAM 2, SAM-H… | 30 | 1295 | active |
| zju3dv/MatchAnything MatchAnything is a deep learning model for universal cross-modality image matching, released as research code accompanying a TPAMI 2026 pap… | 64 | 1293 | active |
| BishopFox/eyeballer Eyeballer is a convolutional neural network tool that classifies screenshots of web hosts taken during large-scope penetration tests. It la… | 51 | 1293 | active |
| Xiangyue-Zhang/auto-deep-researcher-24x7 An open-source Python framework where LLM agents autonomously run deep learning experiments 24/7, covering hypothesis formation, code imple… | 50 | 1293 | active |
| xinychen/transdim transdim is a Python/Jupyter Notebook project providing machine learning models for transportation data imputation and spatiotemporal time … | 59 | 1292 | active |
| locuslab/TCN PyTorch implementation of Temporal Convolutional Networks (TCN) with benchmarks from the paper 'An Empirical Evaluation of Generic Convolut… | 32 | 4569 | maintenance |
| plaidml/plaidml PlaidML is a portable tensor compiler that enables deep learning on hardware (especially GPUs and embedded devices) not well supported by m… | 10 | 4566 | maintenance |
| RoyalVane/CLAN Official PyTorch implementation of CLAN, a CVPR 2019 (oral) / TPAMI 2022 method for unsupervised domain adaptation in semantic segmentation… | 32 | 1289 | stable |
| ELLA ELLA is an Efficient Large Language Model Adapter that equips text-to-image diffusion models with LLM-based text understanding via a Timest… | 26 | 1289 | active |
| e3nn/e3nn e3nn is a Python/PyTorch library for building E(3)-equivariant neural networks that respect 3D rotation, translation, and mirror symmetries… | 64 | 1288 | active |
| vipshop/cache-dit Cache-DiT is a PyTorch-native inference engine that accelerates Diffusion Transformer (DiT) models with hybrid caching, parallelism, quanti… | 79 | 1287 | active |
| Chevron7Locked/kima-hub Kima Hub is a self-hosted, on-demand audio streaming platform that brings a Spotify-like experience to your personal music library, includi… | 78 | 1286 | active |
| Phantom-video/HuMo HuMo is a research model and Python codebase from Tsinghua University and ByteDance for human-centric video generation using collaborative … | 43 | 1286 | active |
| city-super/Scaffold-GS Scaffold-GS is a research implementation of a structured 3D Gaussian splatting method that uses anchor points on a sparse voxel grid to dis… | 27 | 1286 | active |
| flutter-ml/google_ml_kit_flutter A set of Flutter plugins wrapping Google's ML Kit on-device machine learning APIs for Android and iOS. It provides vision APIs (barcode, fa… | 75 | 1285 | active |
| nv-tlabs/Difix3D Difix3D+ is a research codebase from NVIDIA implementing a single-step diffusion model pipeline that removes artifacts from NeRF and 3D Gau… | 29 | 1285 | active |
| DreamTechAI/Direct3D-S2 Direct3D-S2 is a research framework for high-resolution 3D shape generation from images, built on sparse volumetric representations and a n… | 26 | 1285 | active |
| nicodv/kmodes A Python library implementing the k-modes and k-prototypes clustering algorithms for categorical and mixed numerical/categorical data. It f… | 23 | 1285 | stable |
| kubeai-project/kubeai KubeAI is a Kubernetes operator for serving machine learning models in production, supporting LLMs via vLLM and Ollama, vector embeddings, … | 95 | 1284 | active |
| X-Square-Robot/wall-x Wall-X is the open-source training and inference stack for X Square Robot's WALL series of embodied foundation models (VLAs) for general-pu… | 61 | 1283 | active |
| poetiq-ai/poetiq-arc-agi-solver A Python research codebase that reproduces Poetiq's record-breaking, leaderboard-topping submissions to the ARC-AGI-1 and ARC-AGI-2 abstrac… | 39 | 1283 | active |
| BachiLi/diffvg diffvg is a differentiable rasterizer for 2D vector graphics that bridges the raster and vector domains via backpropagation. It computes pi… | 38 | 1283 | active |
| Nixtla/mlforecast mlforecast is a Python framework for time series forecasting using any machine learning model with fit/predict methods, providing efficient… | 94 | 1282 | active |
| dcharatan/pixelsplat pixelSplat is a PyTorch implementation of a feed-forward model that reconstructs 3D radiance fields parameterized by 3D Gaussian primitives… | 27 | 1282 | stable |
| opendatalab/LabelLLM LabelLLM is an open-source data annotation platform designed to streamline the labeling workflows needed for LLM development. It offers con… | 62 | 1281 | active |
| kellyvv/PhoneClaw PhoneClaw is a mobile-native local AI agent framework that turns phones into on-device agent runtimes, running Gemma models via LiteRT and … | 71 | 1279 | active |
| DreamLM/Dream Dream 7B is an open diffusion large language model (dLLM) with base and instruct checkpoints, plus inference and training code built on Hug… | 40 | 1279 | active |
| Tianxiaomo/pytorch-YOLOv4 A minimal PyTorch implementation of YOLOv4 (and YOLOv4-tiny) supporting inference and training, with tools to convert Darknet weights to Py… | 32 | 4520 | maintenance |
| suragnair/alpha-zero-general A clean, flexible implementation of the AlphaZero self-play reinforcement learning algorithm that can be adapted to any two-player turn-bas… | 32 | 4520 | maintenance |
| AaronJackson/vrn Research code for the ICCV 2017 paper 'Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression'. It uses… | 32 | 4518 | maintenance |
| DeepEyes DeepEyes is a research project that trains multimodal vision-language models to 'think with images' using end-to-end reinforcement learning… | 40 | 1278 | active |
| Stable-X/Stable3DGen Stable3DGen is a modular Python framework for generating 3D assets from images, adapted from Microsoft's TRELLIS with NVIDIA library depend… | 30 | 1278 | active |
| SimonBlanke/Gradient-Free-Optimizers A Python library for gradient-free optimization of black-box functions, offering 23 algorithms (hill climbing, Bayesian optimization, parti… | 91 | 1277 | active |
| argmin-rs/argmin argmin is a numerical optimization library written entirely in pure Rust, offering a wide range of optimization algorithms behind a consist… | 54 | 1277 | active |
| ModelCloud/GPTQModel GPTQModel is a production-ready Python toolkit for quantizing (compressing) large language models using GPTQ, AWQ, and related methods, wit… | 92 | 1276 | active |
| Tencent-Hunyuan/SRPO SRPO is Tencent Hunyuan's research code for fine-tuning diffusion image generation models (e.g., FLUX.1.dev) by aligning the full diffusion… | 51 | 1276 | active |
| nianticlabs/monodepth2 Monodepth2 is the reference PyTorch implementation of the ICCV 2019 paper 'Digging into Self-Supervised Monocular Depth Prediction'. It tra… | 32 | 4504 | maintenance |
| Renumics/spotlight Renumics Spotlight is an open-source tool for interactively exploring unstructured datasets (images, audio, text, video, time-series, meshe… | 89 | 1275 | active |
| Linketic/CityGaussian Official implementation of the CityGaussian series (ECCV 2024, ICLR 2025) for high-quality large-scale 3D scene reconstruction with Gaussia… | 63 | 1275 | active |
| JoyCaption JoyCaption is an open, free, and uncensored image captioning Visual Language Model (VLM) with released weights and training scripts. It gen… | 50 | 1275 | active |
| google-research/simclr Google Research's official implementation of SimCLR and SimCLRv2, a framework for contrastive learning of visual representations, with 65 p… | 10 | 4503 | maintenance |
| MilaNLProc/contextualized-topic-models A Python library implementing Contextualized Topic Models (CTM), which combine pre-trained contextual embeddings like BERT with neural topi… | 43 | 1274 | active |
| lpiccinelli-eth/UniDepth UniDepth is a Python library and research codebase for universal monocular metric depth estimation from single images, based on CVPR 2024 a… | 32 | 1274 | active |
| Dex Retargeting A Python library of retargeting optimizers that translate human hand motion (from video or pose datasets) into robot dexterous hand joint c… | 32 | 1274 | active |
| Ma-Lab-Berkeley/CRATE CRATE is the official PyTorch implementation of the Coding RAte reduction TransformEr, a family of 'white-box' transformer architectures de… | 30 | 1274 | active |
| ShiftHackZ/Stable-Diffusion-KMP SDAI is an open-source, cross-platform Stable Diffusion client app for Android and iOS built with Kotlin Multiplatform and Jetpack Compose.… | 92 | 1273 | active |
| magenta/magenta-studio Magenta Studio is a collection of five MIDI music generation plugins (Continue, Generate, Interpolate, Groove, Drumify) for Ableton Live, b… | 59 | 1272 | active |