function: machine-learning
5378 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| spotify/pedalboard Pedalboard is a Python library by Spotify for reading, writing, and processing audio, with built-in effects like reverb, distortion, and EQ… | 93 | 6280 | active |
| meta-llama/llama3 The official Meta repository for Llama 3, providing model weights download scripts, tokenizer, and minimal example code for running inferen… | 10 | 29247 | maintenance |
| gepa-ai/gepa GEPA is a Python framework that optimizes textual system parameters such as prompts, code, and agent configurations using LLM-based reflect… | 83 | 6254 | active |
| tyiannak/pyAudioAnalysis pyAudioAnalysis is a Python library for audio analysis covering feature extraction (MFCCs, spectrograms, chromagrams), supervised and unsup… | 48 | 6254 | active |
| flashinfer-ai/flashinfer FlashInfer is a GPU kernel library and kernel generator for LLM inference, providing unified APIs for attention, GEMM, and MoE operations w… | 90 | 6252 | active |
| RangiLyu/nanodet NanoDet-Plus is a super fast, lightweight anchor-free object detection model implemented in PyTorch, with model sizes as small as 980KB (IN… | 23 | 6252 | stable |
| meta-pytorch/gpt-fast A minimal (<1000 lines) PyTorch-native implementation of fast transformer text generation, demonstrating low-latency LLM inference with int… | 44 | 6249 | active |
| gnuradio/gnuradio GNU Radio is a free and open-source signal processing runtime and development toolkit for building software-defined radios and simulating w… | 67 | 6236 | stable |
| ByteDance-Seed/Depth-Anything-3 Depth Anything 3 (DA3) is a transformer-based model that predicts spatially consistent depth and geometry from any number of visual inputs,… | 59 | 6213 | active |
| Trusted-AI/adversarial-robustness-toolbox Adversarial Robustness Toolbox (ART) is a Python library for machine learning security covering evasion, poisoning, extraction, and inferen… | 55 | 6204 | stable |
| NEKOparapa/AiNiee AiNiee is an AI-powered translation tool focused on automatically translating complex long-form content such as RPG/SLG game text, Epub/TXT… | 94 | 6174 | active |
| skorch-dev/skorch skorch is a Python library that wraps PyTorch neural networks in a scikit-learn compatible API, providing estimators like NeuralNetClassifi… | 85 | 6173 | active |
| ByteDance-Seed/Bagel BAGEL is an open-source unified multimodal foundation model with 7B active parameters (14B total) trained on interleaved multimodal data. I… | 55 | 6159 | active |
| microsoft/fara Fara1.5 is a family of open-weight computer use agent (CUA) models from Microsoft Research, released at 4B, 9B, and 27B scales and built on… | 58 | 6153 | active |
| timeseriesAI/tsai tsai is an open-source deep learning library built on PyTorch and fastai for time series and sequential data tasks such as classification, … | 84 | 6111 | active |
| Akegarasu/lora-scripts SD-Trainer is a GUI application and set of scripts for training LoRA and Dreambooth fine-tunes of Stable Diffusion diffusion models, wrappi… | 66 | 6110 | active |
| deezer/spleeter Spleeter is Deezer's music source separation library with pretrained TensorFlow models that splits audio into stems (vocals, drums, bass, p… | 62 | 28402 | maintenance |
| bytedance/MegaTTS3 MegaTTS 3 is ByteDance's open-source PyTorch text-to-speech model with a lightweight 0.45B-parameter Diffusion Transformer backbone. It pro… | 59 | 6091 | active |
| FederatedAI/FATE FATE (Federated AI Technology Enabler) is an industrial-grade open-source federated learning framework hosted by the Linux Foundation. It e… | 23 | 6089 | active |
| open-edge-platform/anomalib Anomalib is a Python deep learning library for anomaly detection, offering state-of-the-art unsupervised algorithms for detecting and local… | 98 | 6088 | active |
| shimat/opencvsharp OpenCvSharp is a cross-platform .NET wrapper for the OpenCV computer vision library, published as NuGet packages with bundled native binari… | 98 | 6072 | active |
| svc-develop-team/so-vits-svc A deep learning framework based on SoftVC VITS for singing voice conversion (SVC), letting users train models that convert one singing voic… | 10 | 28125 | maintenance |
| bytedance/LatentSync LatentSync is an end-to-end lip-sync framework from ByteDance based on audio-conditioned latent diffusion models, using Stable Diffusion to… | 33 | 6026 | active |
| om-ai-lab/VLM-R1 VLM-R1 is a framework for training R1-style large vision-language models using reinforcement learning (GRPO) on top of Qwen2.5-VL. It provi… | 63 | 6015 | active |
| Doubiiu/ToonCrafter ToonCrafter is a generative model that interpolates two cartoon images into a short animation by leveraging pre-trained image-to-video diff… | 29 | 6003 | stable |
| OFA-Sys/Chinese-CLIP Chinese-CLIP is a Chinese version of the CLIP model trained on ~200 million Chinese image-text pairs, built on open_clip. It provides APIs,… | 66 | 5998 | active |
| chaiNNer-org/chaiNNer chaiNNer is a free, open-source, node-based desktop application for building image processing pipelines by connecting nodes on a canvas. Or… | 81 | 5994 | active |
| uber/causalml Causal ML is a Python package providing uplift modeling and causal inference methods built on machine learning algorithms. It estimates the… | 88 | 5973 | stable |
| z-lab/dflash DFlash is a lightweight block diffusion model used as a draft model for speculative decoding of large language models, drafting entire toke… | 71 | 5967 | active |
| lucidrains/x-transformers A concise PyTorch library implementing full-attention transformer architectures (encoder, decoder, encoder-decoder, and vision transformers… | 85 | 5942 | active |
| online-ml/river River is a Python library for online machine learning, allowing models to learn incrementally from streaming data one observation at a time… | 94 | 5924 | active |
| lxfater/inpaint-web A free, open-source browser-based tool for image inpainting (object removal) and image upscaling (super-resolution), built with WebGPU and … | 53 | 5912 | active |
| ChaoningZhang/MobileSAM MobileSAM is the official implementation of a lightweight version of Meta's Segment Anything Model (SAM), replacing the heavyweight image e… | 65 | 5858 | stable |
| PaddlePaddle/PaddleClas PaddleClas is a Python library and toolkit for image classification, recognition, and retrieval built on the PaddlePaddle deep learning fra… | 66 | 5838 | active |
| kserve/kserve KServe is a CNCF incubating, Kubernetes-native platform for serving both generative and predictive AI models at scale. It provides a standa… | 94 | 5834 | stable |
| SamuelSchmidgall/AgentLaboratory Agent Laboratory is an end-to-end autonomous research workflow framework that uses specialized LLM-driven agents to assist human researcher… | 38 | 5809 | active |
| xiph/rnnoise RNNoise is a C library that uses a hybrid DSP/recurrent neural network approach for real-time full-band speech noise suppression. It also s… | 26 | 5801 | stable |
| amazon-science/chronos-forecasting Chronos is a Python library providing pretrained foundation models for time series forecasting, including Chronos-2 which handles univariat… | 88 | 5759 | active |
| facebookresearch/fastText fastText is a lightweight open-source C++ library (with Python bindings and a CLI) from Facebook Research for efficiently learning word rep… | 10 | 26534 | maintenance |
| pjreddie/darknet Darknet is an open-source neural network framework written in C and CUDA, best known as the original home of the YOLO real-time object dete… | 32 | 26492 | maintenance |
| shibing624/MedicalGPT MedicalGPT is a Python training framework for building medical-domain large language models using the full ChatGPT-style training pipeline:… | 83 | 5748 | active |
| DeepLabCut/DeepLabCut DeepLabCut is an open-source Python toolbox for markerless 2D and 3D pose estimation of user-defined body parts using deep neural networks … | 89 | 5745 | stable |
| google/gemma_pytorch The official PyTorch implementation of Google's Gemma family of open large language models, including text-only and multimodal variants. It… | 10 | 5719 | active |
| mlpack/mlpack mlpack is a fast, header-only C++ machine learning library built on Armadillo, ensmallen, and cereal, offering a wide range of algorithms f… | 87 | 5703 | stable |
| ladaapp/lada Lada is an open-source tool with both GUI and CLI that restores pixelated/mosaic regions in videos, primarily targeting JAV (Japanese adult… | 65 | 5702 | active |
| HKUDS/AI-Researcher AI-Researcher is an autonomous research system that orchestrates the full scientific research pipeline—from literature review and hypothesi… | 41 | 5701 | active |
| ramjke/Translumo Translumo is a Windows desktop application that performs real-time screen translation by capturing on-screen text with OCR and translating … | 72 | 5697 | active |
| google-deepmind/gemma The official JAX-based Python library from Google DeepMind for running, sampling from, and fine-tuning the Gemma family of open-weight larg… | 87 | 5695 | active |
| meta-pytorch/captum Captum is a model interpretability and understanding library for PyTorch, providing implementations of algorithms like Integrated Gradients… | 81 | 5693 | active |
| open-mmlab/OpenPCDet OpenPCDet is a PyTorch-based open-source toolbox for LiDAR-based 3D object detection. It provides official implementations of models like P… | 53 | 5692 | active |
| apple/ml-depth-pro Depth Pro is Apple's reference implementation of a foundation model for zero-shot metric monocular depth estimation, producing sharp high-r… | 30 | 5683 | active |
| biolab/orange3 Orange is an open-source visual programming toolbox for interactive data mining, machine learning, and data visualization. Users build anal… | 76 | 5677 | stable |
| huggingface/alignment-handbook A collection of robust training recipes and scripts from Hugging Face for aligning large language models with human and AI preferences, cov… | 66 | 5671 | active |
| OpenSenseNova/SenseNova-U1 SenseNova-U is a series of open-weight unified multimodal models (e.g., SenseNova-U1.5-8B-MoT) built on the NEO-unify architecture that com… | 59 | 5668 | active |
| pytorch/torchtitan torchtitan is a PyTorch-native platform for large-scale training of generative AI models, offering a clean-room implementation of PyTorch's… | 79 | 5667 | active |
| idealo/imagededup imagededup is a Python library for finding exact and near-duplicate images in a collection using perceptual hashing algorithms (PHash, DHas… | 48 | 5666 | stable |
| Gen-Verse/OpenClaw-RL OpenClaw-RL is a framework for training personalized AI agents through reinforcement learning using natural conversation as feedback. It us… | 52 | 5655 | active |
| Fanghua-Yu/SUPIR SUPIR is a Python-based photo-realistic image restoration system built on SDXL diffusion priors and LLaVA captioning, presented at CVPR 202… | 36 | 5649 | active |
| MahmoudAshraf97/whisper-diarization A pipeline that combines OpenAI Whisper transcription with speaker diarization using Voice Activity Detection (MarbleNet) and speaker embed… | 75 | 5630 | active |
| fla-org/flash-linear-attention A PyTorch library providing hardware-efficient implementations of emerging sequence model architectures, including linear attention, sparse… | 88 | 5627 | active |
| Vision-CAIR/MiniGPT-4 Official code for MiniGPT-4 and MiniGPT-v2, vision-language models that align a frozen visual encoder with a frozen LLM (Vicuna) via a sing… | 30 | 25627 | maintenance |
| nerfstudio-project/gsplat gsplat is an open-source Python library with CUDA-accelerated, differentiable rasterization of Gaussians, based on 3D Gaussian Splatting fo… | 70 | 5589 | active |
| huggingface/parler-tts Parler-TTS is a lightweight text-to-speech library from Hugging Face that generates high-quality, natural-sounding speech controllable via … | 25 | 5586 | active |
| matterport/Mask_RCNN A Python implementation of the Mask R-CNN model for object detection and instance segmentation, built on Keras and TensorFlow with a ResNet… | 23 | 25567 | maintenance |
| newton-physics/newton Newton is an open-source, GPU-accelerated physics simulation engine built on NVIDIA Warp, targeting roboticists and simulation researchers.… | 86 | 5539 | active |
| mosaicml/composer Composer is an open-source PyTorch-based deep learning training library by MosaicML (now Databricks) for training neural networks faster an… | 65 | 5495 | active |
| spotify/basic-pitch Basic Pitch is a lightweight neural network library from Spotify for automatic music transcription, converting audio recordings of nearly a… | 46 | 5489 | stable |
| LaurentMazare/tch-rs tch-rs is a Rust crate providing thin bindings to the C++ API of PyTorch (libtorch), staying close to the original API. It enables tensor o… | 67 | 5479 | active |
| lyuwenyu/RT-DETR Official implementation of RT-DETR and RT-DETRv2, real-time object detection transformers that outperform YOLO models, in PyTorch and Paddl… | 74 | 5476 | active |
| tensorflow/rust TensorFlow Rust provides idiomatic Rust language bindings for TensorFlow via its C API. It lets Rust programs build and run TensorFlow comp… | 10 | 5476 | active |
| obss/sahi SAHI (Slicing Aided Hyper Inference) is a Python vision library for detecting small objects in large images via sliced/tiled inference, wor… | 99 | 5473 | active |
| BIT-DataLab/Edit-Banana Edit Banana is an open-source Python framework that converts static images and PDFs of diagrams, flowcharts, and charts into fully editable… | 60 | 5469 | active |
| Netflix/vmaf VMAF is Netflix's Emmy-winning perceptual video quality assessment algorithm, provided as a standalone C library (libvmaf) with a wrapping … | 91 | 5460 | stable |
| Vector-Wangel/XLeRobot XLeRobot is an open-source project for building a practical dual-arm mobile home robot for around $660 with under four hours of assembly ti… | 61 | 5456 | active |
| karpathy/minGPT A minimal, clean PyTorch re-implementation of OpenAI's GPT covering both training and inference in roughly 300 lines of code. It is designe… | 32 | 24840 | maintenance |
| xxlong0/Wonder3D Wonder3D is a cross-domain diffusion model that reconstructs high-fidelity textured 3D meshes from a single image in 2-3 minutes. It genera… | 32 | 5425 | active |
| isl-org/MiDaS MiDaS is a Python library with pretrained models for robust monocular depth estimation from a single image, based on the TPAMI 2022 paper a… | 10 | 5420 | stable |
| facebookresearch/sapiens Sapiens is a family of foundation models from Meta Reality Labs for human-centric vision tasks including 2D pose estimation, body-part segm… | 61 | 5418 | active |
| mayocream/koharu Koharu is a local-first desktop application that automates manga translation using machine learning, combining text/bubble detection, OCR, … | 82 | 5410 | active |
| brianpetro/obsidian-smart-connections Smart Connections is an Obsidian plugin that surfaces semantically related notes and excerpts while you write, using a locally-run embeddin… | 93 | 5401 | active |
| apple/coremltools Apple's official Python package for converting machine learning models from TensorFlow, PyTorch, scikit-learn, XGBoost, and LibSVM into the… | 80 | 5399 | active |
| deepseek-ai/DeepSeek-VL2 DeepSeek-VL2 is a series of Mixture-of-Experts vision-language models (Tiny, Small, and 4.5B activated parameters) with inference code and … | 25 | 5374 | active |
| Hillobar/Rope Rope is a GUI-focused desktop application for face swapping that implements the insightface inswapper_128 model. It offers batch swapping, … | 79 | 5367 | active |
| nmslib/hnswlib A header-only C++ library with Python bindings implementing the HNSW algorithm for fast approximate nearest neighbor search. It supports in… | 69 | 5312 | stable |
| ysharma3501/LuxTTS LuxTTS is a lightweight zipvoice-based text-to-speech model for high-quality zero-shot voice cloning, generating clear 48kHz speech at up t… | 54 | 5306 | active |
| NVIDIA/cuml NVIDIA cuML is a GPU-accelerated machine learning library offering scikit-learn-style estimators that run on NVIDIA GPUs via CUDA. It also … | 94 | 5264 | active |
| HIT-SCIR/ltp LTP (Language Technology Platform) is an open-source neural NLP toolkit for Chinese supporting word segmentation, POS tagging, NER, depende… | 55 | 5259 | active |
| microsoft/SynapseML SynapseML (formerly MMLSpark) is an open-source machine learning library built on Apache Spark that provides simple, composable, distribute… | 88 | 5240 | active |
| awslabs/gluonts GluonTS is a Python library for probabilistic time series modeling, focused on deep learning based forecasting models built on PyTorch. It … | 88 | 5227 | 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… | 62 | 5227 | 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… | 95 | 5202 | active |
| Baekalfen/PyBoy PyBoy is a Game Boy and Game Boy Color emulator written in Python, usable both as a standalone terminal application and as an embeddable Py… | 89 | 5193 | 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… | 67 | 5183 | active |
| transformerlab/transformerlab-app Transformer Lab is an open-source desktop application (built with Electron and Python) that provides a unified GUI for training, fine-tunin… | 84 | 5179 | 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 | 5172 | 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… | 85 | 5166 | active |
| maziyarpanahi/openmed OpenMed is a local-first healthcare AI SDK for clinical named-entity recognition and HIPAA PII/PHI de-identification that runs entirely on-… | 83 | 5166 | active |
| timesler/facenet-pytorch A PyTorch library providing pretrained face detection (MTCNN) and facial recognition (Inception ResNet V1) models, ported from the TensorFl… | 42 | 5162 | stable |
| NVIDIAGameWorks/kaolin Kaolin is NVIDIA's PyTorch library of GPU-optimized modules for 3D deep learning research, covering meshes, point clouds, and 3D Gaussian s… | 68 | 5161 | active |
| yisol/IDM-VTON Official implementation of IDM-VTON, an ECCV 2024 paper that improves diffusion models for high-fidelity virtual try-on, swapping garments … | 30 | 5156 | active |