1.opendatalab / MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
+21,502 stars
from 61,630 · score 9.98
Trending repositories
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)
2.pytorch / pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
- neural-network
- autograd
- gpu
- numpy
- deep-learning
- tensor
- +2 more
+6,186 stars
from 98,958 · score 8.73
3.chatfire-AI / huobao-drama
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"
+5,636 stars
from 11,366 · score 8.64
4.index-tts / index-tts
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
- bigvgan
- cross-lingual
- indextts
- text-to-speech
- tts
- voice-clone
- +1 more
+4,778 stars
from 20,165 · score 8.47
5.modular / modular
The Modular Platform (includes MAX & Mojo)
- ai
- language
- machine-learning
- mojo
- modular
- programming-language
- +1 more
+4,326 stars
from 25,770 · score 8.37
6.NVIDIA / cosmos
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.
+4,255 stars
from 8,004 · score 8.36
+3,740 stars
from 29,841 · score 8.23
8.duixcom / Duix-Avatar
🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.
- ai-avatar
- ai-avatars
- digital-human
- video-generation
- cloning
- cloning-tool
- +2 more
+3,410 stars
from 12,819 · score 8.13
9.waooAI / waoowaoo
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.)
- ai-agent
- ai-agents
- film-production
- generative-ai
- short-drama
- storyboard
- +2 more
+2,967 stars
from 11,813 · score 8.00
10.facebookresearch / sam3
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.
+2,841 stars
from 9,364 · score 7.95
11.graphdeco-inria / gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
- computer-graphics
- computer-vision
- radiance-field
+2,816 stars
from 21,602 · score 7.94
12.facefusion / facefusion
Industry leading face manipulation platform
- deepfake
- faceswap
- ai
- deep-fake
- face-swap
- lip-sync
- +1 more
+2,604 stars
from 27,934 · score 7.87
13.mozilla-ai / llamafile
Distribute and run LLMs with a single file.
- cross-platform
- gguf
- llama-cpp
- local-ai
- local-inference
- local-llm
- +3 more
+2,361 stars
from 24,205 · score 7.77
14.Beingpax / VoiceInk
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
+2,218 stars
from 4,808 · score 7.70
15.NVIDIA / Megatron-LM
Ongoing research training transformer models at scale
- large-language-models
- model-para
- transformers
+2,172 stars
from 16,155 · score 7.68
+2,049 stars
from 12,965 · score 7.63
17.rany2 / edge-tts
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge
- tts
- speech-synthesis
- text-to-speech
+1,735 stars
from 10,720 · score 7.46
18.facebookresearch / vggt
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
+1,614 stars
from 12,986 · score 7.39
19.colmap / colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
- structure-from-motion
- multi-view-stereo
- reconstruction
- geometry
- computer-vision
+1,577 stars
from 11,574 · score 7.36
20.SakanaAI / AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
+1,557 stars
from 13,388 · score 7.35
21.facebookresearch / dinov3
Reference PyTorch implementation and models for DINOv3
+1,455 stars
from 10,225 · score 7.28
22.cube-js / cube
📊 Cube Core is open-source semantic layer for AI, BI and embedded analytics
- analytics
- cube
- postgresql
- mysql
- bigquery
- sql
- +13 more
+1,323 stars
from 19,844 · score 7.19
23.KlingAIResearch / LivePortrait
Bring portraits to life!
- image-animation
- video-editing
- video-generation
- face-animation
+1,276 stars
from 18,116 · score 7.15
24.CompVis / stable-diffusion
A latent text-to-image diffusion model
+1,116 stars
from 72,457 · score 7.02
25.vwxyzjn / cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
- wandb
- reinforcement-learning
- pytorch
- python
- gym
- machine-learning
- +10 more
+998 stars
from 9,640 · score 6.91
26.Tencent / ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
- inference
- high-preformance
- simd
- arm-neon
- deep-learning
- artificial-intelligence
- +14 more
+917 stars
from 23,105 · score 6.82
27.CorentinJ / Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
- deep-learning
- pytorch
- tensorflow
- tts
- voice-cloning
- python
+879 stars
from 59,344 · score 6.78
28.Tencent-Hunyuan / HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
- video-generation
- diffusion-models
- diffusion-transformer
+757 stars
from 11,967 · score 6.63
29.CMU-Perceptual-Computing-Lab / openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
- openpose
- computer-vision
- machine-learning
- cpp
- caffe
- opencv
- +14 more
+643 stars
from 33,908 · score 6.47
30.sinaptik-ai / pandas-ai
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
+624 stars
from 23,303 · score 6.44
31.NVIDIA / nccl
Optimized primitives for collective multi-GPU communication
- communications
- cpp
- cuda
- deep-learning
- gpu
- nvidia
+549 stars
from 4,662 · score 6.31
32.mlfoundations / open_clip
An open source implementation of CLIP.
- deep-learning
- pytorch
- computer-vision
- language-model
- multi-modal-learning
- contrastive-loss
- +2 more
+547 stars
from 13,697 · score 6.31
33.Unity-Technologies / ml-agents
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.
- reinforcement-learning
- unity3d
- deep-learning
- unity
- deep-reinforcement-learning
- neural-networks
- +1 more
+535 stars
from 19,283 · score 6.28
34.OpenTalker / SadTalker
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
- audio-driven-talking-face
- cvpr2023
- talking-head
- deep-fake
- deep-fakes
- image-animation
- +3 more
+509 stars
from 13,669 · score 6.23
35.TencentARC / GFPGAN
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
- pytorch
- gan
- deep-learning
- super-resolution
- face-restoration
- image-restoration
- +1 more
+468 stars
from 37,233 · score 6.15
36.RunanywhereAI / runanywhere-sdks
Production ready toolkit to run AI locally
+428 stars
from 9,905 · score 6.06
37.sczhou / CodeFormer
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
- codebook
- codeformer
- face-enhancement
- face-restoration
- pytorch
- super-resolution
- +2 more
+401 stars
from 17,809 · score 6.00
38.openai / gpt-2Archived
Code for the paper "Language Models are Unsupervised Multitask Learners"
- paper
+336 stars
from 24,677 · score 5.82
+279 stars
from 2,842 · score 5.63
40.junyanz / pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
- pytorch
- gan
- cyclegan
- pix2pix
- deep-learning
- computer-vision
- +5 more
+274 stars
from 25,000 · score 5.62
41.PointCloudLibrary / pcl
Point Cloud Library (PCL)
- pcl
- c-plus-plus
- cpp
- pointcloud
- computer-vision
- point-cloud
+270 stars
from 10,934 · score 5.60
42.NVlabs / instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
+267 stars
from 17,319 · score 5.59
43.evilsocket / pwnagotchi
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
- ai
- deep-reinforcement-learning
- wpa-psk
- handshakes
- bettercap
- deep-learning
- +1 more
+254 stars
from 8,995 · score 5.54
44.logpai / loghub
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
- logs
- unstructured-logs
- log-analysis
- log-parsing
- datasets
- anomaly-detection
- +1 more
+247 stars
from 2,657 · score 5.51
45.babysor / MockingBird
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
+236 stars
from 36,642 · score 5.47
46.uber / causalml
Uplift modeling and causal inference with machine learning algorithms
- incubation
- machine-learning
- causal-inference
- uplift-modeling
+235 stars
from 5,805 · score 5.46
47.openai / gymArchived
A toolkit for developing and comparing reinforcement learning algorithms.
+214 stars
from 37,017 · score 5.37
48.facebookresearch / xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
+193 stars
from 10,382 · score 5.27
49.facebookresearch / seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
+187 stars
from 11,716 · score 5.24
50.raulmur / ORB_SLAM2
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
+171 stars
from 10,100 · score 5.15
51.facebookresearch / pytorch3d
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
+170 stars
from 9,823 · score 5.14
52.kaldi-asr / kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
- kaldi
- c-plus-plus
- cuda
- shell
- speech-recognition
- speech-to-text
- +3 more
+162 stars
from 15,346 · score 5.09
53.stanfordnlp / stanza
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
+158 stars
from 7,748 · score 5.07
+152 stars
from 26,358 · score 5.03
55.pycaret / pycaret
Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.
- data-science
- python
- machine-learning
- pycaret
- ml
- regression
- +9 more
+138 stars
from 9,720 · score 4.93
56.XingangPan / DragGAN
Official Code for DragGAN (SIGGRAPH 2023)
- artificial-intelligence
- generative-adversarial-network
- generative-models
- image-manipulation
+133 stars
from 35,576 · score 4.90
57.mlpack / mlpack
mlpack: a fast, header-only C++ machine learning library
- machine-learning-library
- c-plus-plus
- deep-learning
- nearest-neighbor-search
- regression
- machine-learning
- +1 more
+123 stars
from 5,599 · score 4.82
58.ShiqiYu / libfacedetection
An open source library for face detection in images. The face detection speed can reach 1000FPS.
- face-detection
- cnn
- arm
+120 stars
from 12,691 · score 4.80
59.alicevision / AliceVision
3D Computer Vision Framework
- computer-vision
- 3d-reconstruction
- photogrammetry
- structure-from-motion
- camera-tracking
- multiview-stereo
- +7 more
+118 stars
from 3,409 · score 4.78
60.BVLC / caffe
Caffe: a fast open framework for deep learning.
+117 stars
from 34,437 · score 4.77
61.matterport / Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
- mask-rcnn
- tensorflow
- object-detection
- instance-segmentation
- keras
+112 stars
from 25,463 · score 4.73
62.googlecreativelab / quickdraw-datasetArchived
Documentation on how to access and use the Quick, Draw! Dataset.
- dataset
- quickdraw-dataset
+106 stars
from 6,690 · score 4.67
+100 stars
from 1,345 · score 4.62
64.brian-team / brian2
Brian is a free, open source simulator for spiking neural networks.
- python
- neuroscience
- science
- differential-equations
- spiking-neural-networks
- biological-simulations
- +5 more
+93 stars
from 1,164 · score 4.54
65.VowpalWabbit / vowpal_wabbit
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.
- c-plus-plus
- machine-learning
- online-learning
- contextual-bandits
- reinforcement-learning
- active-learning
- +2 more
+87 stars
from 8,646 · score 4.48
66.haifengl / smile
Statistical Machine Intelligence & Learning Engine
- machine-learning
- regression
- clustering
- manifold-learning
- nlp
- visualization
- +14 more
+85 stars
from 6,344 · score 4.45
67.flairNLP / flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
+82 stars
from 14,315 · score 4.42
68.junyanz / CycleGAN
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
- gan
- generative-adversarial-network
- deep-learning
- image-generation
- image-manipulation
- cyclegan
- +5 more
+78 stars
from 12,797 · score 4.37
69.mlmed / torchxrayvision
TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.
- medical-imaging
- medical-ai
- deep-learning
- machine-learning
- transfer-learning
- dataset
- +13 more
+77 stars
from 1,138 · score 4.36
70.rasbt / mlxtend
A library of extension and helper modules for Python's data analysis and machine learning libraries.
- python
- machine-learning
- data-science
- data-mining
- association-rules
- supervised-learning
- +1 more
+75 stars
from 5,115 · score 4.33
71.NVlabs / stylegan
StyleGAN - Official TensorFlow Implementation
+72 stars
from 14,338 · score 4.29
72.microsoft / CNTKArchived
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
- cognitive-toolkit
- cntk
- deep-learning
- machine-learning
- deep-neural-networks
- neural-network
- +5 more
+69 stars
from 17,514 · score 4.25
+68 stars
from 10,012 · score 4.23
+68 stars
from 4,284 · score 4.23
75.hjwdzh / QuadriFlow
QuadriFlow: A Scalable and Robust Method for Quadrangulation
- quadriflow
- quad
- remeshing
- quadrangulation
- geometry
+65 stars
from 817 · score 4.19
76.phillipi / pix2pix
Image-to-image translation with conditional adversarial nets
- computer-vision
- computer-graphics
- gan
- pix2pix
- dcgan
- generative-adversarial-network
- +4 more
+64 stars
from 10,596 · score 4.17
77.alievk / avatarify-python
Avatars for Zoom, Skype and other video-conferencing apps.
+63 stars
from 16,440 · score 4.16
+63 stars
from 7,537 · score 4.16
+61 stars
from 2,388 · score 4.13
80.liuliu / ccv
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
+57 stars
from 7,195 · score 4.06
81.AIGC-Audio / AudioGPT
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
+56 stars
from 10,110 · score 4.04
82.SeldonIO / seldon-core
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
- kubernetes
- machine-learning
- deployment
- serving
- mlops
- aiops
- +2 more
+53 stars
from 4,732 · score 3.99
83.dbkangaroo / kangaroo
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.
+52 stars
from 466 · score 3.97
84.automl / SMAC3
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
- bayesian-optimization
- bayesian-optimisation
- hyperparameter-optimization
- hyperparameter-tuning
- hyperparameter-search
- configuration
- +5 more
+50 stars
from 1,218 · score 3.93
85.NVlabs / stylegan2
StyleGAN2 - Official TensorFlow Implementation
+47 stars
from 11,135 · score 3.87
86.SeldonIO / alibi-detect
Algorithms for outlier, adversarial and drift detection
- anomaly
- outlier
- concept-drift
- detection
- unsupervised-learning
- semi-supervised-learning
- +7 more
+46 stars
from 2,508 · score 3.85
87.mahmoodlab / CONCH
Vision-Language Pathology Foundation Model - Nature Medicine
- bioimage-analysis
- bioimage-informatics
- conch
- foundation-model
- health-informatics
- histopathology
- +9 more
+46 stars
from 494 · score 3.85
88.horovod / horovodArchived
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
- tensorflow
- uber
- machine-learning
- machinelearning
- mpi
- baidu
- +7 more
+43 stars
from 14,632 · score 3.78
89.jina-ai / clip-as-service
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
- clip-as-service
- bert-as-service
- +9 more
+42 stars
from 12,792 · score 3.76
+39 stars
from 9,101 · score 3.69
91.NVIDIA / FastPhotoStyle
Style transfer, deep learning, feature transform
+37 stars
from 11,135 · score 3.64
92.src-d / hercules
Gaining advanced insights from Git repository history.
- git-analysis
- machine-learning
- tensorflow
- git
- mloncode
- tensorboard-visualizations
- +2 more
+36 stars
from 2,774 · score 3.61
93.SeldonIO / alibi
Algorithms for explaining machine learning models
- machine-learning
- explanations
- interpretability
- counterfactual
- xai
+36 stars
from 2,615 · score 3.61
94.QingyongHu / RandLA-Net
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)
- semantic-segmentation
- 3d-vision
- computer-vision
- semantic3d
- s3dis
- semantickitti
+34 stars
from 1,533 · score 3.56
95.xinshuoweng / AB3DMOT
(IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"
- computer-vision
- machine-learning
- robotics
- tracking
- 3d-tracking
- multi-object-tracking
- +9 more
+31 stars
from 1,819 · score 3.47
96.chenfei-wu / TaskMatrix
The repository host gives no description.
+28 stars
from 33,887 · score 3.37
97.tensorlayer / TensorLayer
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
+28 stars
from 7,358 · score 3.37
98.dmis-lab / biobert
Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining
+28 stars
from 2,187 · score 3.37
99.tiny-dnn / tiny-dnn
header only, dependency-free deep learning framework in C++14
- c-plus-plus
- deep-learning
- machine-learning
- neural-network
+27 stars
from 6,001 · score 3.33
+27 stars
from 1,303 · score 3.33