1.opendatalab / MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Ranked by Attention Score: stars gained over the last 180 complete days
1–100 of 172 by Attention Score · May 9, 2026 – Nov 4, 2026 (UTC)
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Translated🎬 火宝短剧 (Huobao Short Drama) - An AI-based one-stop short drama generation platform 《Generate a complete short drama from one sentence, fully automated from script to final video》 Huobao Drama - An AI-Powered End-to-End Short Drama Generator "One Sentence to Complete Drama: Fully Automated from Script to Final Video"
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
The Modular Platform (includes MAX & Mojo)
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.
TranslatedIndustry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows. (The Chinese part states: the first industrial-grade, full-pipeline AI film and video production platform.)
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Industry leading face manipulation platform
Distribute and run LLMs with a single file.
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
Ongoing research training transformer models at scale
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
COLMAP - Structure-from-Motion and Multi-View Stereo
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Reference PyTorch implementation and models for DINOv3
📊 Cube Core is open-source semantic layer for AI, BI and embedded analytics
Bring portraits to life!
A latent text-to-image diffusion model
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Clone a voice in 5 seconds to generate arbitrary speech in real-time
HunyuanVideo: A Systematic Framework For Large Video Generation Model
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Optimized primitives for collective multi-GPU communication
An open source implementation of CLIP.
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Production ready toolkit to run AI locally
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Code for the paper "Language Models are Unsupervised Multitask Learners"
Image-to-Image Translation in PyTorch
Point Cloud Library (PCL)
Instant neural graphics primitives: lightning fast NeRF and more
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
Uplift modeling and causal inference with machine learning algorithms
A toolkit for developing and comparing reinforcement learning algorithms.
Hackable and optimized Transformers building blocks, supporting a composable construction.
Foundational Models for State-of-the-Art Speech and Text Translation
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
kaldi-asr/kaldi is the official location of the Kaldi project.
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.
Official Code for DragGAN (SIGGRAPH 2023)
mlpack: a fast, header-only C++ machine learning library
An open source library for face detection in images. The face detection speed can reach 1000FPS.
3D Computer Vision Framework
Caffe: a fast open framework for deep learning.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Documentation on how to access and use the Quick, Draw! Dataset.
Brian is a free, open source simulator for spiking neural networks.
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
Statistical Machine Intelligence & Learning Engine
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.
A library of extension and helper modules for Python's data analysis and machine learning libraries.
StyleGAN - Official TensorFlow Implementation
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
QuadriFlow: A Scalable and Robust Method for Quadrangulation
Image-to-image translation with conditional adversarial nets
Avatars for Zoom, Skype and other video-conferencing apps.
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
Kangaroo is an AI-powered SQL client and admin tool for popular databases (MariaDB / MySQL / Oracle / PostgreSQL / Redis / SQLite / SQL Server / ...) on Windows / MacOS / Linux, support table design, query, model, sync, export/import etc, focus on comfortable, fun and developer friendly.
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
StyleGAN2 - Official TensorFlow Implementation
Algorithms for outlier, adversarial and drift detection
Vision-Language Pathology Foundation Model - Nature Medicine
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
Style transfer, deep learning, feature transform
Gaining advanced insights from Git repository history.
Algorithms for explaining machine learning models
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)
(IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"
The repository host gives no description.
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining
header only, dependency-free deep learning framework in C++14