1.tensorflow / tensorflow
An Open Source Machine Learning Framework for Everyone
+7,346 stars
from 193,944 · score 8.90
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
99 repositories by Attention Score · May 8, 2026 – Nov 3, 2026 (UTC)
2.ggml-org / whisper.cpp
Port of OpenAI's Whisper model in C/C++
+5,803 stars
from 49,091 · score 8.67
3.opencv / opencv
Open Source Computer Vision Library
+4,588 stars
from 86,843 · score 8.43
4.tesseract-ocr / tesseract
Tesseract Open Source OCR Engine (main repository)
- tesseract
- tesseract-ocr
- ocr
- lstm
- machine-learning
- ocr-engine
- +1 more
+3,803 stars
from 73,521 · score 8.24
5.k2-fsa / sherpa-onnx
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
+3,756 stars
from 11,956 · score 8.23
+3,195 stars
from 25,848 · score 8.07
7.HIllya51 / LunaTranslator
TranslatedVisual Novel Translator
- galgame
- visual-novel
- translator
- reverse-engineering
- ocr
+2,740 stars
from 11,272 · score 7.92
8.google-ai-edge / mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
- mediapipe
- c-plus-plus
- computer-vision
- deep-learning
- android
- video-processing
- +11 more
+2,638 stars
from 34,901 · score 7.88
9.mozilla-ai / llamafile
Distribute and run LLMs with a single file.
- cross-platform
- gguf
- llama-cpp
- local-ai
- local-inference
- local-llm
- +3 more
+2,358 stars
from 24,197 · score 7.77
10.microsoft / onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
- deep-learning
- onnx
- neural-networks
- machine-learning
- ai-framework
- hardware-acceleration
- +3 more
+1,902 stars
from 20,316 · score 7.55
11.colmap / colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
- structure-from-motion
- multi-view-stereo
- reconstruction
- geometry
- computer-vision
+1,576 stars
from 11,566 · score 7.36
12.alibaba / MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
- mnn
- convolution
- vulkan
- embedded-devices
- winograd-algorithm
- machine-learning
- +5 more
+1,344 stars
from 15,003 · score 7.20
+1,092 stars
from 14,488 · score 7.00
14.openvinotoolkit / openvino
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
- inference
- deep-learning
- openvino
- ai
- computer-vision
- diffusion-models
- +13 more
+989 stars
from 10,122 · score 6.90
15.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
+923 stars
from 23,100 · score 6.83
16.lightgbm-org / LightGBM
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
- gbdt
- gbm
- machine-learning
- data-mining
- distributed
- lightgbm
- +7 more
+718 stars
from 18,229 · score 6.58
17.dmlc / xgboost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
- gbdt
- gbrt
- gbm
- distributed-systems
- xgboost
- machine-learning
+713 stars
from 28,228 · score 6.57
18.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
+645 stars
from 33,907 · score 6.47
19.NVIDIA / nccl
Optimized primitives for collective multi-GPU communication
- communications
- cpp
- cuda
- deep-learning
- gpu
- nvidia
+546 stars
from 4,661 · score 6.30
20.NVIDIA / TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
- tensorrt
- nvidia
- deep-learning
- inference
- gpu-acceleration
+540 stars
from 12,891 · score 6.29
21.rhasspy / piperArchived
A fast, local neural text to speech system
- speech-synthesis
- text-to-speech
- tts
+511 stars
from 10,805 · score 6.24
22.RunanywhereAI / runanywhere-sdks
Production ready toolkit to run AI locally
+433 stars
from 9,900 · score 6.07
23.Const-me / Whisper
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
+417 stars
from 10,283 · score 6.04
24.google / sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
- neural-machine-translation
- natural-language-processing
- word-segmentation
+414 stars
from 11,750 · score 6.03
25.PaddlePaddle / Paddle
TranslatedPArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (Core framework of 'PaddlePaddle' (飞桨, Feijiang), for deep learning & machine learning: high-performance single-machine and distributed training, and cross-platform deployment)
- paddlepaddle
- deep-learning
- scalability
- machine-learning
- neural-network
- python
- +2 more
+386 stars
from 23,748 · score 5.96
26.catboost / catboost
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
- machine-learning
- decision-trees
- gradient-boosting
- gbm
- gbdt
- python
- +12 more
+319 stars
from 8,873 · score 5.77
+307 stars
from 2,420 · score 5.73
28.PointCloudLibrary / pcl
Point Cloud Library (PCL)
- pcl
- c-plus-plus
- cpp
- pointcloud
- computer-vision
- point-cloud
+273 stars
from 10,933 · score 5.61
29.mkiol / dsnote
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
- asr
- sailfishos
- stt
- tts
- flatpak-applications
- linux-desktop
- +9 more
+267 stars
from 1,440 · score 5.59
+211 stars
from 10,015 · score 5.36
31.sail-sg / envpool
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
- reinforcement-learning
- parallel-processing
- cpp17
- pybind11
- reinforcement-learning-environments
- threadpool
- +10 more
+203 stars
from 1,330 · score 5.32
32.CopterExpress / clover
ROS-based framework and RPi image to control PX4-powered drones 🍀
- ros
- px4
- mavros
- aruco
- quadcopter
- computer-vision
- +5 more
+203 stars
from 491 · score 5.32
33.activeloopai / deeplake
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
- deep-learning
- pytorch
- ai
- mlops
- computer-vision
- datalake
- +13 more
+193 stars
from 9,072 · score 5.27
34.raulmur / ORB_SLAM2
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
+172 stars
from 10,099 · score 5.15
35.interpretml / interpret
Fit interpretable models. Explain blackbox machine learning.
- machine-learning
- interpretability
- gradient-boosting
- blackbox
- scikit-learn
- xai
- +13 more
+157 stars
from 6,819 · score 5.06
36.davisking / dlib
A toolkit for making real world machine learning and data analysis applications in C++
- machine-learning
- deep-learning
- c-plus-plus
- python
- computer-vision
- machine-learning-library
- +1 more
+156 stars
from 14,313 · score 5.06
37.DayBreak-u / chineseocr_lite
TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M
+133 stars
from 12,223 · score 4.90
38.mozilla / DeepSpeechArchived
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
+128 stars
from 26,644 · score 4.86
39.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 5,598 · score 4.82
40.uxlfoundation / oneDNN
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
- x64
- aarch64
- +14 more
+123 stars
from 3,964 · score 4.82
41.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
42.alicevision / AliceVision
3D Computer Vision Framework
- computer-vision
- 3d-reconstruction
- photogrammetry
- structure-from-motion
- camera-tracking
- multiview-stereo
- +7 more
+117 stars
from 3,409 · score 4.77
43.BVLC / caffe
Caffe: a fast open framework for deep learning.
+116 stars
from 34,437 · score 4.76
+113 stars
from 11,364 · score 4.74
45.Farama-Foundation / ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
- deep-learning
- reinforcement-learning
- python
- vizdoom
- doom
- examples
- +2 more
+105 stars
from 2,004 · score 4.66
+100 stars
from 1,345 · score 4.62
47.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
48.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
49.hjwdzh / QuadriFlow
QuadriFlow: A Scalable and Robust Method for Quadrangulation
- quadriflow
- quad
- remeshing
- quadrangulation
- geometry
+65 stars
from 817 · score 4.19
+62 stars
from 2,388 · score 4.14
51.liuliu / ccv
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
+57 stars
from 7,194 · score 4.06
52.flashlight / flashlight
A C++ standalone library for machine learning
- flashlight
- machine-learning
- autograd
- cpp
- deep-learning
- neural-network
- +1 more
+53 stars
from 5,426 · score 3.99
53.ankitdhall / lidar_camera_calibration
ROS package to find a rigid-body transformation between a LiDAR and a camera for "LiDAR-Camera Calibration using 3D-3D Point correspondences"
+49 stars
from 1,727 · score 3.91
54.leela-zero / leela-zero
Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
+48 stars
from 5,545 · score 3.89
55.Devsh-Graphics-Programming / Nabla
Vulkan, OptiX and CUDA Interoperation Modular Rendering Library and Framework for PC/Linux/Android
- vulkan
- raytracing
- graphics-engine
- graphics-library
- optix
- optix-denoiser
- +12 more
+41 stars
from 681 · score 3.74
56.ZigRazor / CXXGraph
Header-Only C++ Library for Graph Representation and Algorithms
- search-algorithm
- dijkstra-algorithm
- graph
- graph-algorithms
- graph-theory-algorithms
- graph-analysis
- +14 more
+39 stars
from 699 · score 3.69
57.ginkgo-project / ginkgo
Numerical linear algebra software package
- linear-algebra
- hpc
- gpu-computing
- cuda
- krylov-methods
- preconditioning
- +6 more
+39 stars
from 591 · score 3.69
58.apache / mxnetArchived
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
- mxnet
+38 stars
from 20,755 · score 3.66
59.crow-translate / crow-translateArchived
A simple and lightweight translator that allows you to translate and speak text using Google, Yandex Bing, LibreTranslate and Lingva.
+33 stars
from 1,931 · score 3.53
60.hyye / lio-mapping
Implementation of Tightly Coupled 3D Lidar Inertial Odometry and Mapping (LIO-mapping)
- sensor-fusion
- slam
- mapping
- icra2019
+33 stars
from 1,001 · score 3.53
+31 stars
from 2,702 · score 3.47
62.tiny-dnn / tiny-dnn
header only, dependency-free deep learning framework in C++14
- c-plus-plus
- deep-learning
- machine-learning
- neural-network
+28 stars
from 6,001 · score 3.37
63.shogun-toolbox / shogun
Shōgun
- machine-learning
- data-science
- artificial-intelligence
- swig
- c-plus-plus
- cmake
+27 stars
from 3,057 · score 3.33
64.libfann / fann
Official github repository for Fast Artificial Neural Network Library (FANN)
- fann
- c
- neural-network
- library
+26 stars
from 1,722 · score 3.30
65.shrec / UltrafastSecp256k1
Ultra high-performance secp256k1 ECC engine | Python, Node.js, Rust, Go, C#, Swift, Java bindings | CUDA, Metal, OpenCL GPU | ECDSA, Schnorr, FROST, MuSig2, BIP-352 | 15+ platforms
- cryptography
- cuda
- riscv
- secp256k1
- arm64
- opencl
- +14 more
+25 stars
from 36 · score 3.26
+24 stars
from 2,438 · score 3.22
67.apple / turicreateArchived
Turi Create simplifies the development of custom machine learning models.
+23 stars
from 11,131 · score 3.18
+23 stars
from 2,212 · score 3.18
69.eyalroz / cuda-api-wrappers
Thin, unified, C++-flavored wrappers for the CUDA APIs
+23 stars
from 883 · score 3.18
70.PRBonn / semantic_suma
SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)
- rangenet-lib
- suma
- lidar
- slam
- semantic
- 3d-lidar
- +1 more
+21 stars
from 998 · score 3.09
+18 stars
from 1,620 · score 2.94
72.esa / pygmo2
A Python platform to perform parallel computations of optimisation tasks (global and local) via the asynchronous generalized island model.
- optimization
- optimization-algorithms
- optimization-methods
- optimization-problem
- evolutionary-algorithms
- multiobjective-optimization
- +9 more
+17 stars
from 527 · score 2.89
73.flashlight / wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
- wav2letter
- speech-recognition
- end-to-end
- deep-learning
- cpp
+16 stars
from 6,427 · score 2.83
74.robotology / yarp
YARP - Yet Another Robot Platform
- middleware
- yarp
- robotics-libraries
- robotics
- devices
- humanoids
- +8 more
+16 stars
from 590 · score 2.83
75.gvinciguerra / PGM-index
🏅State-of-the-art learned data structure that enables fast lookup, predecessor, range searches and updates in arrays of billions of items using orders of magnitude less space than traditional indexes
- data-structures
- database
- cpp
- research
- indexing
- big-data
- +8 more
+13 stars
from 865 · score 2.64
76.Tessil / hat-trie
C++ implementation of a fast and memory efficient HAT-trie
- cpp
- trie
- hat-trie
- data-structures
- header-only
- c-plus-plus
+13 stars
from 862 · score 2.64
77.stillwater-sc / universal
Large collection of number systems providing custom arithmetic for mixed-precision algorithm development and optimization for AI, Machine Learning, Computer Vision, Signal Processing, CAE, EDA, control, optimization, estimation, and approximation.
- arithmetic
- integer-arithmetic
- fixed-point-arithmetic
- rational-arithmetic
- floating-point-arithmetic
- posit-arithmetic
- +13 more
+10 stars
from 493 · score 2.40
78.Xtra-Computing / thundersvm
ThunderSVM: A Fast SVM Library on GPUs and CPUs
+9 stars
from 1,618 · score 2.30
+9 stars
from 808 · score 2.30
80.meta-toolkit / meta
A Modern C++ Data Sciences Toolkit
- nlp
- nlp-parsing
- search-engine
- inverted-index
- pos-tag
- text-analysis
- +6 more
+9 stars
from 712 · score 2.30
81.abreheret / PixelAnnotationTool
Annotate quickly images.
- computer-vision
- deep-learning
- pixel-wise
- ground-truth
- annotation-tool
- opencv
- +7 more
+8 stars
from 1,447 · score 2.20
82.Dobiasd / frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
- tensorflow
- deep-learning
- keras
- cpp
- cpp14
- header-only
- +10 more
+8 stars
from 1,121 · score 2.20
83.aksnzhy / xlearn
High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.
- machine-learning
- statistics
- data-science
- data-analysis
- factorization-machines
- ffm
- +1 more
+7 stars
from 3,083 · score 2.08
84.niessner / VoxelHashing
[Siggraph Asia 2013] Large-Scale, Real-Time 3D Reconstruction
- 3d-reconstruction
- kinect
- computer-vision
+7 stars
from 704 · score 2.08
85.uxlfoundation / oneDAL
oneAPI Data Analytics Library (oneDAL)
- onedal
- data-analysis
- oneapi
- machine-learning
- machine-learning-algorithms
- hacktoberfest
- +8 more
+7 stars
from 646 · score 2.08
86.Xtra-Computing / thundergbm
ThunderGBM: Fast GBDTs and Random Forests on GPUs
- cuda
- gpu
- gbdt
- random-forest
- machine-learning
+5 stars
from 711 · score 1.79
+5 stars
from 702 · score 1.79
88.AICAN-Research / FAST-Pathology
⚡ Open-source software for deep learning-based digital pathology
- deep-learning
- machine-learning
- digital-pathology
- computational-pathology
- software
- free-to-use
- +11 more
+5 stars
from 141 · score 1.79
89.cnadler86 / mp_esp_dl_models
Micropython binding for the ESP32 DL AI vision models like face detection / recognition, imagenet classifier or pedestrian (human) detection
- esp32
- face-detection
- imagenet-classifier
- micropython
- pedestrian-detection
- ai
- +1 more
+4 stars
from 12 · score 1.61
90.NVIDIA / libcudacxxArchived
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
+3 stars
from 2,297 · score 1.39
91.dmlc / minervaArchived
Minerva: a fast and flexible tool for deep learning on multi-GPU. It provides ndarray programming interface, just like Numpy. Python bindings and C++ bindings are both available. The resulting code can be run on CPU or GPU. Multi-GPU support is very easy.
+3 stars
from 709 · score 1.39
92.gagolews / stringi
Fast and Portable Character String Processing in R (with the Unicode ICU)
+3 stars
from 317 · score 1.39
93.intel / ros2_openvino_toolkit
This repository provides a set of tools and libraries to integrate Intel® OpenVINO™ Toolkit with ROS 2 (Robot Operating System), enabling efficient deployment of deep learning models for computer vision applications on Intel® hardware.
+3 stars
from 185 · score 1.39
94.facebookarchive / beringeiArchived
Beringei is a high performance, in-memory storage engine for time series data.
+2 stars
from 3,146 · score 1.10
+2 stars
from 914 · score 1.10
+2 stars
from 885 · score 1.10
97.ANNetGPGPU / ANNetGPGPU
A GPU (CUDA) based Artificial Neural Network library
- self-organizing-map
- cuda
- c-plus-plus-11
- propagation-network
+2 stars
from 112 · score 1.10
98.jubatus / jubatus
Framework and Library for Distributed Online Machine Learning
- machine-learning
- c-plus-plus
- ml
- distributed
+1 stars
from 705 · score 0.69
+1 stars
from 53 · score 0.69