function: machine-learning
5378 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| ianarawjo/ChainForge ChainForge is an open-source visual programming environment for battle-testing prompts to LLMs, built on ReactFlow and Flask. It lets users… | 73 | 3026 | active |
| deepnote/deepnote Deepnote is an open-source, AI-first drop-in replacement for Jupyter notebooks with a human-readable YAML format, block-based architecture … | 79 | 3000 | active |
| NVIDIA/NeMo-Retriever NVIDIA's scalable document content and metadata extraction library (also known as NVIDIA Ingest) that splits documents, classifies and extr… | 86 | 2973 | active |
| signerless/llm-checker A Node.js CLI tool that scans your hardware (GPU, VRAM, CPU, memory) and recommends which LLM or small language models you can run locally,… | 84 | 2951 | active |
| KevinWang676/Bark-Voice-Cloning A one-click hub of Gradio Web UIs and Colab notebooks for open-source voice cloning, TTS, and voice conversion models including Bark, GPT-S… | 67 | 2947 | active |
| sherlockchou86/VideoPipe VideoPipe is a C++ framework for video analysis and structuring that works like a pipeline of independent, composable nodes. It integrates … | 53 | 2934 | active |
| michaelfeil/infinity Infinity is a high-throughput, low-latency serving engine that exposes text-embedding, reranking, CLIP, CLAP and ColPali models via an Open… | 63 | 2933 | active |
| ax-llm/ax Ax is a TypeScript-first LLM programming framework implementing the DSPy model, providing typed signatures, agents, flows, and optimizers l… | 94 | 2891 | active |
| jhj0517/Whisper-WebUI A Gradio-based web interface for OpenAI's Whisper models that generates subtitles from files, YouTube videos, or microphone input. It suppo… | 63 | 2870 | active |
| bytedeco/javacpp-presets JavaCPP Presets provides Java bindings for commonly used native C++ libraries such as OpenCV, FFmpeg, and many others, built on the JavaCPP… | 86 | 2850 | active |
| whylabs/whylogs whylogs is an open-source Python data logging library for machine learning models and data pipelines. It profiles datasets with privacy-pre… | 34 | 2831 | active |
| openalpr/openalpr OpenALPR is an open-source Automatic License Plate Recognition (ALPR) library written in C++ that analyzes images and video streams to dete… | 23 | 11456 | maintenance |
| google-research/kubric Kubric is a data generation pipeline from Google Research for creating semi-realistic synthetic multi-object videos with rich annotations l… | 60 | 2813 | active |
| RoboTwin-Platform/RoboTwin RoboTwin 2.0 is a scalable benchmark and data-generation platform for bimanual (dual-arm) robotic manipulation, built on simulated digital … | 69 | 2808 | active |
| mll-lab-nu/RAGEN RAGEN is a Python framework for training reasoning LLM agents with multi-turn reinforcement learning using the StarPO algorithm. It also pr… | 65 | 2789 | active |
| ModelTC/LightX2V LightX2V is a lightweight, high-performance inference framework for image and video generation, supporting tasks like text-to-video, image-… | 65 | 2777 | active |
| FluidInference/FluidAudio A Swift SDK providing fully local, low-latency audio AI on Apple devices, including speech-to-text (Parakeet), speaker diarization (Pyannot… | 81 | 2727 | active |
| CVCUDA/CV-CUDA CV-CUDA is an open-source GPU-accelerated library of computer vision and image processing operators built on CUDA, with C++ and Python APIs… | 93 | 2723 | active |
| freedmand/semantra-python Semantra is a command-line tool that semantically indexes text and PDF documents and launches a local web application for querying them by … | 30 | 2711 | active |
| xdit-project/xDiT xDiT is a scalable inference engine for Diffusion Transformers (DiTs) that enables parallel deployment across multiple GPUs and machines. I… | 92 | 2706 | active |
| UKGovernmentBEIS/inspect_ai Inspect is an open-source Python framework from the UK AI Security Institute for running large language model evaluations, with composable … | 72 | 2696 | active |
| spotify/scio Scio is a Scala API for Apache Beam and Google Cloud Dataflow, inspired by Apache Spark and Scalding. It provides a unified batch and strea… | 96 | 2628 | active |
| NVlabs/LongLive LongLive is an NVIDIA research framework providing parallel training and inference infrastructure for real-time long video generation, usin… | 60 | 2592 | active |
| Memento-Teams/Memento Memento is a Python framework for building LLM agents that continually improve from experience via memory-based case-based reasoning, witho… | 38 | 2568 | active |
| YeQing17-2026/OmniAgent OmniAgent is an open-source Python agent framework that self-evolves across skills, context, memory, and its underlying model during intera… | 57 | 2557 | active |
| AIGC-Audio/AudioGPT AudioGPT is a Python framework that wraps multiple audio foundation models (for speech, singing, sound, and talking-head tasks) behind a GP… | 30 | 10168 | maintenance |
| microsoft/foundry-local Foundry Local is Microsoft's end-to-end local AI runtime and SDK suite (C#, JavaScript, Python, Rust) for running optimized models entirely… | 87 | 2538 | active |
| facebookresearch/nougat Nougat is Meta's neural OCR model that parses academic PDFs into structured Markdown, understanding LaTeX math and tables. It ships as a Py… | 23 | 10071 | maintenance |
| janhq/ichigo Ichigo is a Python speech package for developers offering local realtime voice AI capabilities, including a compact 22M-parameter speech to… | 49 | 2489 | active |
| xuebinqin/U-2-Net Official PyTorch implementation of U^2-Net, a nested U-structure deep network for salient object detection, published in Pattern Recognitio… | 32 | 9856 | maintenance |
| microsoft/PIKE-RAG PIKE-RAG is a Microsoft framework for building Retrieval-Augmented Generation systems that extract, understand, and apply specialized domai… | 31 | 2481 | active |
| mirage-project/mirage Mirage Persistent Kernel (MPK) is a compiler and runtime that transforms multi-GPU LLM inference into a single fused megakernel, reducing i… | 83 | 2474 | active |
| data-infra/cube-studio CubeStudio is an open-source, cloud-native, all-in-one AI platform covering the full machine learning lifecycle (MLOps/MaaS/LLMOps), includ… | 79 | 2473 | active |
| Zleap-AI/SAG SAG is an open-source retrieval architecture and knowledge base application that replaces both traditional RAG and GraphRAG with event-enti… | 84 | 2460 | active |
| nz-m/SocialEcho SocialEcho is a full-featured social networking platform built on the MERN stack (MongoDB, Express.js, React.js, Node.js) with automated co… | 31 | 2435 | active |
| snapotter-hq/SnapOtter SnapOtter is an open-source, self-hosted file-processing suite offering 200+ tools across image, video, audio, PDF, and document modalities… | 80 | 2412 | active |
| ailia-ai/ailia-models A collection of 400+ pre-trained state-of-the-art AI models (object detection, pose estimation, speech recognition, LLMs, image generation,… | 77 | 2389 | active |
| showlab/Paper2Video Paper2Video is a Python pipeline that automatically generates academic presentation videos from scientific papers, taking a paper PDF, a sp… | 49 | 2373 | active |
| eikek/docspell Docspell is a self-hosted document management system (DMS) for organizing scanned papers, e-mails, and other files. It automates metadata t… | 68 | 2317 | active |
| claimed-framework/claimed CLAIMED (C3) is a component compiler that turns Jupyter notebooks, Python scripts, and R scripts into portable containerized AI components.… | 88 | 2305 | active |
| togethercomputer/OpenChatKit OpenChatKit is an open-source toolkit from Together, LAION, and Ontocord.ai for building and fine-tuning chat language models, including in… | 30 | 8983 | maintenance |
| casadi/casadi CasADi is an open-source symbolic framework for gradient-based numerical optimization, implementing forward and reverse mode automatic diff… | 91 | 2284 | stable |
| langfengQ/verl-agent verl-agent is an extension of the veRL framework for training LLM and VLM agents via reinforcement learning, featuring step-independent mul… | 56 | 2276 | active |
| PrismML-Eng/Bonsai-demo A demo repository for running PrismML's Bonsai family of 1-bit and ternary-quantized language models locally via llama.cpp and MLX. It prov… | 59 | 2272 | active |
| IBM/AssetOpsBench AssetOpsBench is an open-source benchmark and framework from IBM for building, orchestrating, and evaluating domain-specific AI agents for … | 64 | 2256 | active |
| 0xShug0/audio.cpp audio.cpp is a pure C++ inference engine for audio models built on ggml, supporting TTS, STT, VAD, voice conversion, music generation, and … | 81 | 2249 | active |
| wxyhgk/retain-pdf RetainPDF is an open-source PDF translation tool that preserves layout, formulas, and document structure, with special support for scanned/… | 82 | 2238 | active |
| DanOps-1/Gpt-Agreement-Payment A Python toolkit that reverse-engineers and replays the end-to-end ChatGPT Plus/Team/Pro subscription payment flow (Stripe Checkout, PayPal… | 53 | 2238 | active |
| dstackai/dstack dstack is an open-source, vendor-agnostic control plane for GPU provisioning and orchestration that works across GPU clouds, Kubernetes, an… | 96 | 2236 | active |
| learnhouse/learnhouse LearnHouse is a next-generation open-source learning management system (LMS) for creating, sharing, and selling educational content. It com… | 99 | 2234 | active |
| TommyLemon/APIAuto APIAuto is a web-based HTTP API tool combining machine-learning-powered no-code automated testing, code generation with static checks, and … | 86 | 2218 | active |
| MVIG-SJTU/AlphaPose AlphaPose is an open-source real-time multi-person full-body pose estimation and tracking system built on PyTorch. It detects human keypoin… | 32 | 8600 | maintenance |
| unrealcv/unrealcv UnrealCV is an open-source Unreal Engine plugin that connects computer vision research to virtual worlds by exposing a command API and Pyth… | 88 | 2209 | active |
| TimmyOVO/deepseek-ocr.rs A Rust implementation of the DeepSeek-OCR inference stack with multiple OCR/VLM backends (DeepSeek-OCR, PaddleOCR-VL, DotsOCR), DSQ quantiz… | 60 | 2184 | active |
| intel/intel-extension-for-transformers Intel's toolkit for accelerating transformer-based GenAI/LLM workloads on Intel platforms, offering state-of-the-art compression (e.g., INT… | 10 | 2173 | active |
| boson-ai/higgs-audio Higgs Audio is a text-audio foundation model project from Boson AI providing code and weights for conversational text-to-speech with zero-s… | 56 | 8339 | maintenance |
| HUANGCHIHHUNGLeo/claude-real-video A Python CLI tool and agent skill that lets LLMs like Claude actually watch videos by extracting scene-aware, deduplicated keyframes plus a… | 80 | 2116 | active |
| GAIR-NLP/daVinci-MagiHuman daVinci-MagiHuman is an open-source 15B-parameter single-stream transformer foundation model that jointly generates synchronized audio and … | 49 | 2115 | active |
| A-EDev/Flow Flow is an open-source, privacy-respecting YouTube and YouTube Music client for Android built with Kotlin and Jetpack Compose (Material 3).… | 84 | 2108 | active |
| LeCAR-Lab/ASAP ASAP is a two-stage framework for training agile humanoid whole-body skills by aligning simulation and real-world physics. It pre-trains mo… | 47 | 2107 | active |
| QwenLM/Qwen2-Audio Official repository for Qwen2-Audio, a 7B-parameter large audio-language model from Alibaba Cloud that accepts audio inputs and responds to… | 31 | 2099 | active |
| raphaelmansuy/edgequake EdgeQuake is a high-performance Graph-RAG framework written in Rust, inspired by LightRAG, that transforms documents (PDFs, markdown, text)… | 79 | 2084 | active |
| visomaster/VisoMaster VisoMaster is a Python-based desktop application for AI-powered face swapping and face editing in images and videos. It supports multiple s… | 27 | 2068 | active |
| Plachtaa/VALL-E-X An open-source Python implementation of Microsoft's VALL-E X zero-shot text-to-speech model, with a community-trained pretrained checkpoint… | 10 | 7930 | maintenance |
| gocrane/crane Crane is a FinOps platform for cloud resource analytics and cost optimization in Kubernetes clusters. It provides cost insight, optimizatio… | 23 | 2054 | active |
| microsoft/foundry-dev-tools Microsoft Foundry Toolkit (formerly AI Toolkit) is a Visual Studio Code extension for building, testing, and deploying AI agents and models… | 80 | 2050 | active |
| ainfosec/FISSURE FISSURE is an open-source RF and reverse engineering framework built around software-defined radios, supporting signal detection, classific… | 77 | 2039 | active |
| HKUDS/MiniRAG MiniRAG is an extremely simple retrieval-augmented generation framework designed to work with small, open-source language models. It uses s… | 39 | 2008 | active |
| praat/praat.github.io Praat is a desktop application for analyzing, synthesizing, and manipulating speech, widely used in phonetics research and teaching. It pro… | 99 | 1971 | stable |
| showlab/computer_use_ootb An out-of-the-box desktop GUI agent that lets vision-language models like Claude 3.5 Computer Use, ShowUI, and UI-TARS control Windows and … | 32 | 1958 | active |
| chn-lee-yumi/MaterialSearch MaterialSearch is a self-hosted semantic search tool that indexes local photos and videos using a CLIP multimodal model, letting users find… | 73 | 1957 | active |
| kenforthewin/atomic Atomic is a self-hosted, local-first personal knowledge base that turns markdown notes into a semantically-connected, AI-augmented knowledg… | 77 | 1945 | active |
| google-deepmind/lab DeepMind Lab is a customisable 3D learning environment built on Quake III Arena (ioquake3) that provides navigation and puzzle-solving task… | 23 | 7372 | maintenance |
| LCAV/pyroomacoustics Pyroomacoustics is a Python package for audio signal processing in indoor scenarios, combining a fast C++ room acoustics simulator (image s… | 90 | 1930 | stable |
| chthollyphile/folia-major Folia is an online music player focused on immersive full-screen lyrics animations, supporting NetEase Cloud Music, KuGou, Navidrome, and l… | 80 | 1910 | active |
| oficcejo/aiagents-stock A Python multi-AI-agent stock analysis and monitoring system for mainland China A-shares, simulating a team of securities analysts to produ… | 53 | 1902 | active |
| baetyl/baetyl Baetyl is an open-source edge computing framework from Linux Foundation Edge that extends cloud computing, data, and services to edge devic… | 23 | 1900 | active |
| AutoArk/EVA-OS EVA OS / EVA Platform is a real-time multimodal AI operating system and development platform for next-generation smart hardware, combining … | 68 | 1890 | active |
| flybirdxx/ComfyUI-Qwen-TTS A ComfyUI custom node plugin that wraps Alibaba's Qwen3-TTS model for speech synthesis, zero-shot voice cloning, and natural-language voice… | 54 | 1884 | active |
| MontrealCorpusTools/Montreal-Forced-Aligner Montreal Forced Aligner is a command line utility for time-aligning orthographic transcriptions and pronunciation dictionary entries to aud… | 98 | 1876 | active |
| we0091234/Chinese_license_plate_detection_recognition A PyTorch-based Chinese license plate detection and recognition system built on YOLOv5 for detection and CRNN for recognition. It supports … | 70 | 1869 | active |
| AutoFigure AutoFigure-Edit is a Python application that converts scientific paper method sections into fully editable SVG figures using large language… | 55 | 1867 | active |
| gaomingqi/Track-Anything Track-Anything is an interactive tool for video object tracking and segmentation built on Segment Anything, XMem, and E2FGVI. Users specify… | 55 | 6997 | maintenance |
| YangLing0818/RPG-DiffusionMaster Official implementation of RPG (Recaption, Plan, Generate), a training-free framework that uses multimodal LLMs as prompt recaptioners and … | 27 | 1844 | active |
| HKUDS/VideoAgent VideoAgent is an all-in-one agentic framework for video understanding, editing, and remaking, built on multi-agent orchestration with over … | 60 | 1838 | active |
| ROCm/FastFlowLM FastFlowLM (FLM) is an NPU-first LLM inference runtime purpose-built and deeply optimized for AMD Ryzen AI NPUs (XDNA2), offering an Ollama… | 86 | 1836 | active |
| undertheseanlp/underthesea Underthesea is an open-source Python toolkit for Vietnamese natural language processing that has evolved into an agentic AI toolkit with mu… | 94 | 1803 | active |
| dreadl0ck/netcap Netcap is a Go framework that converts network packets into structured, type-safe Protocol Buffer audit records for security monitoring, fo… | 92 | 1803 | active |
| HybridRobotics/berkeley-humanoid-lite Berkeley Humanoid Lite is the open-source codebase for a sub-$5,000 3D-printed humanoid robot platform from UC Berkeley. It includes Isaac … | 55 | 1802 | active |
| SmartFlowAI/EmoLLM EmoLLM is a series of open-source large language models fine-tuned for mental health understanding and support, built on models like Intern… | 59 | 1781 | active |
| neuml/paperai paperai is an AI application for medical and scientific papers that runs bulk LLM inference and RAG pipelines over article repositories to … | 67 | 1779 | active |
| Emu Series Emu3 is a suite of state-of-the-art multimodal models from BAAI trained solely with next-token prediction, tokenizing images, text, and vid… | 56 | 1779 | active |
| beam-cloud/beta9 Beam (beta9) is an open-source serverless runtime for AI workloads, providing GPU inference endpoints, isolated sandboxes for running untru… | 90 | 1766 | active |
| signerlabs/Klee Klee is a native macOS AI chat application that runs large language models entirely on-device using Apple's MLX framework on Apple Silicon.… | 55 | 1761 | active |
| x007xyz/flycut-caption FlyCut Caption is an AI-powered video subtitle editing tool built as a React component and web/desktop app, offering speech recognition wit… | 78 | 1757 | active |
| 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… | 59 | 1755 | 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 | 6547 | maintenance |
| Feather-2/Burner-X Paper Burner X is a browser-based AI workstation for processing, translating, and analyzing academic documents like PDFs, DOCX, PPTX, and E… | 51 | 1752 | 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 … | 86 | 1751 | active |
| lf-edge/ekuiper LF Edge eKuiper is a lightweight stream processing engine for IoT edge devices, offering SQL-based and graph-based rule engine for real-tim… | 99 | 1733 | active |