domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| LeeSureman/Flat-Lattice-Transformer Reference implementation of the ACL 2020 paper FLAT: Chinese NER Using Flat-Lattice Transformer, built on PyTorch and FastNLP. It trains fl… | 32 | 1003 | maintenance |
| giotto-ai/giotto-tda giotto-tda is a high-performance Python toolbox for topological machine learning, built on top of scikit-learn. It provides tools for topol… | 23 | 1002 | maintenance |
| microsoft/nnfusion NNFusion is a flexible and efficient deep neural network (DNN) compiler that generates high-performance executables from model descriptions… | 23 | 1002 | maintenance |
| openai/grok Research code accompanying the paper 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' from OpenAI. It provides t… | 10 | 4261 | experimental |
| MoonshotAI/Attention-Residuals Official implementation of Attention Residuals (AttnRes), a drop-in replacement for standard residual connections in Transformers that lets… | 47 | 3498 | experimental |
| xjdr-alt/entropix Entropix is a research project implementing entropy-based sampling and parallel chain-of-thought decoding for large language models, aiming… | 22 | 3432 | experimental |
| lucidrains/musiclm-pytorch A PyTorch library implementing MusicLM, Google's text-to-music generation model, by combining text-conditioned AudioLM with MuLan, a text-a… | 21 | 3293 | experimental |
| ml-tooling/opyrator Opyrator is a Python library that turns plain Python functions into production-ready microservices with an auto-generated HTTP API (FastAPI… | 67 | 3132 | experimental |
| enhuiz/vall-e An unofficial PyTorch implementation of the VALL-E text-to-speech audio language model, built on the EnCodec tokenizer. It provides trainin… | 31 | 2976 | experimental |
| openai/weak-to-strong OpenAI's research codebase implementing weak-to-strong generalization experiments from their alignment paper, where a strong pretrained mod… | 10 | 2552 | experimental |
| test-time-training/ttt-video-dit Official PyTorch implementation of 'One-Minute Video Generation with Test-Time Training', which finetunes the CogVideoX 5B diffusion transf… | 50 | 2451 | experimental |
| IlyaRice/RAG-Challenge-2 A Python implementation of the winning RAG system from the Enterprise RAG Challenge 2 competition, answering questions about company annual… | 29 | 2438 | experimental |
| facebookresearch/large_concept_model Official PyTorch implementation of Meta's Large Concept Models (LCM), which perform language modeling by autoregressively predicting senten… | 23 | 2376 | experimental |
| dvmazur/mixtral-offloading A Python library enabling efficient inference of Mixtral-8x7B mixture-of-experts language models on limited hardware like Google Colab or c… | 26 | 2334 | experimental |
| google/tangent Tangent is a Python library for automatic differentiation that works by source-to-source transformation: it reads your Python function's so… | 10 | 2328 | experimental |
| MineDojo/NitroGen NitroGen is an open foundation model for generalist gaming agents that takes pixel input from games and predicts gamepad actions, trained v… | 45 | 2174 | experimental |
| Sumandora/remove-refusals-with-transformers A proof-of-concept Python script that removes refusal behavior from LLMs by ablating the refusal direction using pure Hugging Face Transfor… | 48 | 2170 | experimental |
| YiVal/YiVal YiVal is an open-source Python framework that automatically tunes prompts, RAG configurations, and model parameters for generative AI appli… | 19 | 2133 | experimental |
| microsoft/aici AICI (Artificial Intelligence Controller Interface) is a Microsoft Research prototype that lets developers write Wasm-based controllers to … | 19 | 2076 | experimental |
| hyperspaceai/agi Hyperspace AGI is an experimental peer-to-peer network where autonomous AI agents collaboratively train language models and share research … | 82 | 2036 | experimental |
| lucidrains/make-a-video-pytorch A PyTorch library implementing Make-A-Video, Meta AI's text-to-video generation approach, built around pseudo-3d (axial) convolutions and s… | 23 | 1987 | experimental |
| photonixapp/photonix Photonix is a self-hosted, web-based photo management server built with Django and React. It ingests your photo collection and enables smar… | 65 | 1954 | experimental |
| chelsea0x3b/dfdx A Rust deep learning library providing shape-checked tensors and neural network building blocks with compile-time verification of tensor op… | 23 | 1933 | experimental |
| future-agi/future-agi Future AGI is an open-source, self-hostable platform for evaluating, observing, and improving LLM and AI agent applications, combining trac… | 81 | 1919 | experimental |
| matthewearl/deep-anpr An experimental Python project that uses neural networks (TensorFlow) to build an automatic number plate recognition (ANPR) system. It incl… | 32 | 1857 | experimental |
| Continual-Intelligence/SEAL SEAL (Self-Adapting LLMs) is a research framework from MIT CSAIL that trains language models via reinforcement learning to generate their o… | 34 | 1852 | experimental |
| rentruewang/aioway Aioway is an optimizing compiler for deep learning algorithms that treats ML models as instructions and builds declarative pipelines using … | 77 | 1824 | experimental |
| IliasHad/edit-mind Edit Mind is a local-first video knowledge base that indexes video libraries with multi-modal AI analysis (Whisper transcription, YOLO obje… | 76 | 1799 | experimental |
| antirez/voxtral.c A pure C, zero-dependency inference implementation of Mistral's Voxtral Realtime 4B speech-to-text model, with a streaming C API and CLI fo… | 45 | 1743 | experimental |
| google-research/dex-lang Dex is an experimental research programming language from Google Research for typed, functional array processing in the Haskell/ML family. … | 59 | 1696 | experimental |
| Ildaron/Laser_control An open-source hardware and software project that uses a camera, deep learning object detection (Darknet/YOLO via OpenCV), and galvanometer… | 66 | 1609 | experimental |
| EvolvingLMMs-Lab/open-r1-multimodal A fork of Hugging Face's open-r1 that extends the R1 GRPO reinforcement learning training paradigm to multimodal (vision-language) models l… | 23 | 1603 | experimental |
| lyuchenyang/Macaw-LLM Macaw-LLM is a multi-modal language modeling framework that integrates image, video, audio, and text data, built on CLIP, Whisper, and LLaM… | 29 | 1591 | experimental |
| lichao-sun/Mora Mora is an open-source multi-agent framework for generalist video generation, using multiple collaborative visual AI agents to replicate ca… | 25 | 1591 | experimental |
| fedden/poker_ai An open-source Python implementation of a Texas Hold'em poker AI based on Counterfactual Regret Minimization (CFR), inspired by Pluribus. I… | 10 | 1587 | experimental |
| AnswerDotAI/fsdp_qlora A training script/library from Answer.AI that combines QLoRA (quantized LoRA) with PyTorch FSDP to fine-tune large language models like Lla… | 26 | 1549 | experimental |
| fastplotlib/fastplotlib fastplotlib is a GPU-accelerated scientific plotting library for Python built on the pygfx rendering engine, which uses WGPU (Vulkan, DX12,… | 80 | 1524 | experimental |
| graphdeco-inria/hierarchical-3d-gaussians Official implementation of the SIGGRAPH 2024 paper 'A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Dataset… | 35 | 1462 | experimental |
| OpnTec/mvisc MVISC (Mobile Visual Classification) is an application that identifies and classifies individual animals from photos using computer vision,… | 32 | 1384 | experimental |
| sintel-dev/Orion Orion is a Python machine learning library for unsupervised time series anomaly detection, offering verified ML pipelines that flag rare pa… | 74 | 1368 | experimental |
| hughperkins/VeriGPU VeriGPU is an open-source GPU written in SystemVerilog, loosely based on the RISC-V ISA and targeting eventual ASIC tape-out for machine le… | 32 | 1368 | experimental |
| AutoArk/TinyEngram TinyEngram is an open research project exploring DeepSeek-AI's Engram architecture and memory injection as an alternative to LoRA for param… | 53 | 1358 | experimental |
| EthicalML/xai XAI is a Python library from the Institute for Ethical AI & ML that provides tools for analysing and evaluating machine learning datasets a… | 65 | 1260 | experimental |
| KhoomeiK/LlamaGym LlamaGym is a Python library that simplifies fine-tuning LLM-based agents with online reinforcement learning in Gym-style environments. It … | 25 | 1254 | experimental |
| SakanaAI/self-adaptive-llms Transformer² is a research framework from SakanaAI that adapts large language models to unseen tasks in real-time by selectively adjusting … | 23 | 1226 | experimental |
| danielgross/LlamaAcademy LlamaAcademy is a Python pipeline that crawls API documentation, generates synthetic training data with GPT-3.5/GPT-4, and fine-tunes a Vic… | 30 | 1198 | experimental |
| facebookresearch/shumai Shumai is a fast, differentiable tensor library for TypeScript and JavaScript built on Bun and Flashlight (ArrayFire backend). It provides … | 32 | 1172 | experimental |
| kijai/ComfyUI-FluxTrainer A ComfyUI custom node plugin that wraps kohya's sd-scripts to enable LoRA, LyCORIS, and full fine-tune training of FLUX models directly ins… | 29 | 1161 | experimental |
| FinHackCN/finhack FinHack is an extensible Python quantitative finance framework covering the full quant research workflow: data collection, factor computati… | 76 | 1154 | experimental |
| Ligo-Biosciences/AlphaFold3 An open-source Python implementation of AlphaFold3, DeepMind's biomolecular structure prediction model, including the full model architectu… | 27 | 1090 | experimental |
| tantaraio/voy Voy is a tiny vector similarity search engine written in Rust and compiled to WebAssembly, using a k-d tree index for fast nearest-neighbor… | 31 | 1072 | experimental |
| srush/llama2.rs A pure Rust implementation of Llama2 inference optimized for fast CPU execution, featuring 4-bit GPT-Q quantization, SIMD support, and memo… | 28 | 1064 | experimental |
| philippgille/chromem-go chromem-go is an embeddable vector database for Go with a Chroma-like interface and zero third-party dependencies. It runs in-memory with o… | 54 | 1051 | experimental |
| erelsgl/limdu Limdu is a machine-learning framework for Node.js supporting binary, multi-class, and multi-label classification with online and batch lear… | 57 | 1047 | experimental |
| huggingface/optimum-nvidia Optimum-NVIDIA is a Python library that bridges Hugging Face Transformers with NVIDIA TensorRT-LLM for highly optimized LLM inference on NV… | 58 | 1037 | experimental |
| volcengine/veScale veScale is a PyTorch distributed training library from ByteDance for hyperscale training of large language models and reinforcement learnin… | 57 | 1037 | experimental |
| HumanMLLM/R1-Omni R1-Omni is a research project applying Reinforcement Learning with Verifiable Reward (RLVR) to an omni-multimodal large language model for … | 26 | 1025 | experimental |
| Rikj000/MoniGoMani MoniGoMani is a Freqtrade framework and trading strategy for cryptocurrency trading that uses weighted signals optimized via HyperOpt. It i… | 10 | 1025 | experimental |
| orca-wm/Orca Orca is a general world foundation model from BAAI centered on Next-State-Prediction, learning a unified world latent space from visual and… | 57 | 1021 | experimental |
| ronibandini/reggaetonBeGone A Raspberry Pi-based edge machine learning device that continuously samples ambient audio and uses an Edge Impulse audio classification mod… | 70 | 1005 | experimental |
| mozilla/DeepSpeech DeepSpeech is an open-source, offline speech-to-text engine based on Baidu's Deep Speech research paper and implemented with TensorFlow. It… | 10 | 26779 | abandoned |
| facebookresearch/Detectron Facebook AI Research's Python software system implementing state-of-the-art object detection algorithms such as Mask R-CNN, RetinaNet, and … | 10 | 26356 | abandoned |
| HumanSignal/labelImg LabelImg is a graphical image annotation tool written in Python with a Qt interface for drawing bounding boxes on images. It saves annotati… | 10 | 25055 | abandoned |
| apache/mxnet Apache MXNet is a deep learning framework offering a hybrid front-end that mixes imperative (Gluon) and symbolic programming, with a dynami… | 10 | 20810 | abandoned |
| magenta/magenta Magenta is a Google Brain research project and Python TensorFlow library for generating music, images, and drawings with machine learning. … | 10 | 19801 | abandoned |
| jantic/DeOldify DeOldify is a deep learning project for colorizing and restoring old black-and-white images and videos, with artistic and stable model vari… | 10 | 18481 | abandoned |
| microsoft/CNTK The Microsoft Cognitive Toolkit (CNTK) is an open-source deep-learning toolkit that describes neural networks as directed computational gra… | 10 | 17592 | abandoned |
| camenduru/stable-diffusion-webui-colab A collection of Google Colab notebooks that run the AUTOMATIC1111-style Stable Diffusion WebUI in the cloud, with lite/stable/nightly varia… | 48 | 15916 | abandoned |
| horovod/horovod Horovod is a distributed deep learning training framework for TensorFlow, Keras, PyTorch, and Apache MXNet, originally developed at Uber. I… | 10 | 14685 | abandoned |
| supertone-inc/supertonic Supertonic is a lightning-fast, on-device multilingual text-to-speech system powered by ONNX Runtime, with a compact 99M-parameter open-wei… | 58 | 13758 | abandoned |
| apache/predictionio Apache PredictionIO is an open-source machine learning server built on Spark, HBase, Elasticsearch, and Hadoop that lets developers build, … | 10 | 12516 | abandoned |
| alexjc/neural-enhance Neural Enhance is a Python command-line tool that upscales images 2x or 4x using deep learning super-resolution models. It ships with pre-t… | 10 | 11864 | abandoned |
| karpathy/convnetjs ConvNetJS is a JavaScript library for defining and training neural networks, including convolutional networks and an experimental Deep Q Le… | 23 | 11196 | abandoned |
| mistralai/mistral-inference The official minimal Python library from Mistral AI for running inference with Mistral open-weight models such as Mistral 7B, Mixtral, Code… | 10 | 10833 | abandoned |
| Theano/Theano Theano is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays… | 32 | 9998 | abandoned |
| facebookresearch/maskrcnn-benchmark A fast, modular PyTorch reference implementation of instance segmentation and object detection algorithms including Mask R-CNN, Faster R-CN… | 10 | 9361 | abandoned |
| voicepaw/so-vits-svc-fork A fork of so-vits-svc providing singing voice conversion with realtime support and an improved interface, built on PyTorch and PyTorch Ligh… | 82 | 9330 | abandoned |
| Torch7 Torch7 is a scientific computing framework with a fast multi-dimensional tensor library and math operations, originally built for Lua with … | 39 | 9141 | abandoned |
| clips/pattern Pattern is a Python web mining module bundling tools for scraping (Google, Twitter, Wikipedia APIs, crawler, HTML DOM parser), NLP (POS tag… | 66 | 8860 | abandoned |
| intel/ipex-llm IPEX-LLM is a PyTorch LLM acceleration library for Intel hardware (iGPU, NPU, Arc/Flex/Max GPUs, and CPU), offering low-bit quantization (F… | 10 | 8860 | abandoned |
| tensorflow/tfjs-core tfjs-core was the core WebGL-accelerated tensor computation library behind TensorFlow.js, providing linear algebra operations and automatic… | 10 | 8429 | abandoned |
| facebookarchive/caffe2 Caffe2 is a lightweight, modular, and scalable deep learning framework built on the original Caffe, with both Python and C++ APIs. It has b… | 10 | 8371 | abandoned |
| nebuly-ai/optimate OptiMate is a collection of Python libraries from Nebuly AI for optimizing AI model performance, including Speedster for inference accelera… | 23 | 8327 | abandoned |
| rbgirshick/py-faster-rcnn A Python reimplementation of the Faster R-CNN object detection model built on a fork of Fast R-CNN and Caffe. The repository is officially … | 32 | 8289 | abandoned |
| EleutherAI/gpt-neo GPT-Neo is EleutherAI's implementation of model- and data-parallel GPT-3-style transformer language models built on mesh-tensorflow, with r… | 10 | 8268 | abandoned |
| openai/jukebox OpenAI's research code and pretrained model weights for Jukebox, a generative neural network that produces music with vocals as raw audio f… | 10 | 8030 | abandoned |
| harthur/brain A simple feed-forward neural network library written in JavaScript, usable in Node.js and the browser. It supports training on input/output… | 10 | 7988 | abandoned |
| jwyang/faster-rcnn.pytorch A pure PyTorch implementation of Faster R-CNN for object detection, supporting multi-image batch training and multi-GPU training with sever… | 32 | 7857 | abandoned |
| facebookresearch/DensePose DensePose is a research library from Facebook AI that maps all human pixels in 2D RGB images to a 3D surface-based model of the human body … | 10 | 7258 | abandoned |
| carpedm20/DCGAN-tensorflow A TensorFlow implementation of Deep Convolutional Generative Adversarial Networks (DCGAN) for generating images such as faces and digits. I… | 32 | 7179 | abandoned |
| facebookresearch/pytext PyText is a deep-learning-based NLP modeling framework built on PyTorch, providing extensible abstractions for text classifiers, sequence t… | 10 | 6292 | abandoned |
| Hironsan/BossSensor A desktop application that uses a webcam and a trained CNN classifier to detect when a specific person (your boss) approaches, automaticall… | 32 | 6288 | abandoned |
| rustformers/llm An ecosystem of Rust libraries built on GGML for running large language model inference locally, including a CLI binary and reusable crates… | 10 | 6155 | abandoned |
| tensorflow/swift Swift for TensorFlow was an experimental next-generation machine learning platform integrating differentiable programming directly into the… | 10 | 6123 | abandoned |
| Lightning-AI/lit-llama Lit-LLaMA is an independent, Apache 2.0-licensed implementation of the LLaMA language model built on nanoGPT, covering pre-training, fine-t… | 43 | 6085 | abandoned |
| Swift-AI/Swift-AI Swift AI is a high-performance deep learning library written entirely in Swift, offering a flexible fully-connected neural network optimize… | 23 | 6036 | abandoned |
| tiny-dnn/tiny-dnn tiny-dnn is a header-only, dependency-free deep learning framework written in C++14, designed for training and running neural networks on r… | 23 | 6030 | abandoned |
| yahoo/open_nsfw A Python library from Yahoo that runs a Caffe deep neural network to classify images as Not Suitable for Work (NSFW), outputting a probabil… | 10 | 6011 | abandoned |
| oarriaga/face_classification A Python project providing real-time face detection with emotion and gender classification using a Keras CNN trained on fer2013 and IMDB da… | 32 | 5734 | abandoned |
| erikbern/ann-benchmarks A benchmarking environment for approximate nearest neighbor (ANN) search algorithms, with pre-generated HDF5 datasets and Docker containers… | 73 | 5725 | abandoned |