101.google / magika
Fast and accurate AI powered file content types detection
- deep-learning
- filetype
- keras-classification-models
- keras-models
- mime-types
- ai
- +1 more
+929 stars
from 17,833 · score 6.84
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
101–200 of 1,283 by Attention Score · Aug 6, 2026 – Nov 3, 2026 (UTC)
102.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.
+928 stars
from 11,315 · score 6.83
103.mlc-ai / web-llm
High-performance In-browser LLM Inference Engine
- deep-learning
- llm
- tvm
- webgpu
- webml
- chatgpt
- +1 more
+904 stars
from 18,449 · score 6.81
104.STranslate / STranslate
TranslatedA ready-to-go translation ocr tool developed with WPF. A ready-to-use translation and OCR tool developed with WPF
+900 stars
from 7,611 · score 6.80
105.microsoft / TRELLIS
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
- 3d
- 3d-generation
- image-to-3d
- text-to-3d
- 3d-aigc
+877 stars
from 13,310 · score 6.78
106.BasedHardware / omi
AI that sees your screen, listens to your conversations and tells you what to do
+868 stars
from 13,020 · score 6.77
107.tphakala / birdnet-go
Self-hosted realtime soundscape analyser for birds, bats and other wildlife. Multi-model local AI inference, runs 24/7 on a Raspberry Pi.
- audio
- bioacoustics
- birds
- golang
- tensorflow
- birdnet
- +12 more
+867 stars
from 1,526 · score 6.77
108.datalab-to / chandra
OCR model that handles complex tables, forms, handwriting with full layout.
+837 stars
from 11,840 · score 6.73
109.rany2 / edge-tts
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge
- tts
- speech-synthesis
- text-to-speech
+825 stars
from 11,624 · score 6.72
110.NVIDIA-NeMo / Speech
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
- machine-translation
- speaker-recognition
- asr
- tts
- generative-ai
- deeplearning
- +4 more
+813 stars
from 17,878 · score 6.70
111.deepinsight / insightface
State-of-the-art 2D and 3D Face Analysis Project
- face-recognition
- face-detection
- mxnet
- face-alignment
- age-estimation
- arcface
- +4 more
+797 stars
from 29,334 · score 6.68
112.colmap / colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
- structure-from-motion
- multi-view-stereo
- reconstruction
- geometry
- computer-vision
+777 stars
from 12,365 · score 6.66
113.hpcaitech / Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
+774 stars
from 29,138 · score 6.65
+752 stars
from 30,634 · score 6.62
115.openai / tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
+739 stars
from 18,853 · score 6.61
116.huggingface / diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
- deep-learning
- diffusion
- image-generation
- pytorch
- score-based-generative-modeling
- image2image
- +9 more
+732 stars
from 34,124 · score 6.60
117.Farama-Foundation / Shimmy
PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama
- deepmind-control-suite
- deepmind-lab
- gymnasium
- reinforcement-learning
- gymnasium-environment
+710 stars
from 222 · score 6.57
+709 stars
from 16,665 · score 6.57
119.google-research / google-research
Google Research
+706 stars
from 38,395 · score 6.56
120.HumanSignal / label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
- computer-vision
- deep-learning
- image-annotation
- annotation-tool
- annotation
- labeling
- +14 more
+702 stars
from 27,919 · score 6.56
121.Dao-AILab / flash-attention
Fast and memory-efficient exact attention
+699 stars
from 24,545 · score 6.55
122.FluidInference / FluidAudio
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
+680 stars
from 2,577 · score 6.52
123.QuentinFuxa / WhisperLiveKit
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
- python
- real-time
- speaker-diarization
- speech-recognition
- speech-to-text
- streaming
- +6 more
+679 stars
from 10,532 · score 6.52
124.tensortrade-org / tensortrade
An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
+676 stars
from 6,580 · score 6.52
125.cvat-ai / cvat
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
- video-annotation
- computer-vision
- computer-vision-annotation
- image-annotation
- annotation-tool
- annotation
- +14 more
+660 stars
from 16,400 · score 6.49
126.cube-js / cube
📊 Cube Core is open-source semantic layer for AI, BI and embedded analytics
- analytics
- cube
- postgresql
- mysql
- bigquery
- sql
- +13 more
+654 stars
from 20,502 · score 6.48
127.SakanaAI / AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
+652 stars
from 14,285 · score 6.48
128.ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
- yolov5
- object-detection
- pytorch
- onnx
- coreml
- tflite
- +10 more
+647 stars
from 57,603 · score 6.47
129.Starmel / OpenSuperWhisper
macOS dictation app
+642 stars
from 2,473 · score 6.47
130.nobodywho-ooo / nobodywho
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
- godot
- godot-engine
- godot-plugin
- godot4
- llm
- inference-engine
- +14 more
+639 stars
from 1,026 · score 6.46
131.allenai / olmocr
Toolkit for linearizing PDFs for LLM datasets/training
+625 stars
from 19,188 · score 6.44
132.facebookresearch / segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+624 stars
from 54,474 · score 6.44
133.labmlai / annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
- deep-learning
- deep-learning-tutorial
- pytorch
- gan
- transformers
- reinforcement-learning
- +7 more
+623 stars
from 67,049 · score 6.44
134.KlingAIResearch / LivePortrait
Bring portraits to life!
- image-animation
- video-editing
- video-generation
- face-animation
+616 stars
from 18,769 · score 6.42
135.facebookresearch / dinov3
Reference PyTorch implementation and models for DINOv3
+612 stars
from 11,058 · score 6.42
136.twitter / the-algorithm
Source code for the X Recommendation Algorithm
+597 stars
from 73,408 · score 6.39
137.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
+594 stars
from 15,753 · score 6.39
138.c2g-dev / city2graph
Transform geospatial relations into graphs for Graph Neural Networks and spatial network analysis
- network-analysis
- spatial-analysis
- geographical-information-system
- graph-neural-networks
- pytorch-geometric
- geographic-data-science
- +14 more
+590 stars
from 1,368 · score 6.38
139.tracel-ai / burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- autodiff
- deep-learning
- machine-learning
- rust
- scientific-computing
- ndarray
- +12 more
+579 stars
from 15,650 · score 6.36
+565 stars
from 14,444 · score 6.34
141.jax-ml / jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
+564 stars
from 36,008 · score 6.34
142.QwenLM / Qwen
TranslatedThe official repo of Qwen chat & pretrained large language model proposed by Alibaba Cloud.
- chinese
- large-language-models
- natural-language-processing
- flash-attention
- llm
- pretrained-models
+550 stars
from 21,445 · score 6.31
143.Lightricks / LTX-Video
Official repository for LTX-Video
- diffusion-models
- dit
- image-to-video
- image-to-video-generation
- text-to-video
- text-to-video-generation
+548 stars
from 10,750 · score 6.31
144.deepspeedai / DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
- deep-learning
- pytorch
- gpu
- machine-learning
- billion-parameters
- data-parallelism
- +7 more
+541 stars
from 42,749 · score 6.30
145.serengil / deepface
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
- face-recognition
- vgg-face
- facenet
- openface
- facial-expression-recognition
- age-prediction
- +11 more
+540 stars
from 23,105 · score 6.29
146.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
+540 stars
from 10,571 · score 6.29
147.QwenLM / Qwen3-VL
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
+539 stars
from 19,625 · score 6.29
148.joonspk-research / generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
+536 stars
from 21,798 · score 6.29
149.modelscope / DiffSynth-Studio
Enjoy the magic of Diffusion models!
+536 stars
from 12,801 · score 6.29
150.openai / CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
+535 stars
from 34,030 · score 6.28
151.deepfakes / faceswap
Deepfakes Software For All
- faceswap
- face-swap
- deep-learning
- deeplearning
- deep-neural-networks
- deepfakes
- +8 more
+533 stars
from 57,067 · score 6.28
+530 stars
from 23,588 · score 6.27
153.CompVis / stable-diffusion
A latent text-to-image diffusion model
+522 stars
from 73,050 · score 6.26
154.tinygrad / tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
+521 stars
from 33,305 · score 6.26
155.Farama-Foundation / Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
+519 stars
from 12,248 · score 6.25
156.microsoft / JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
- deep-learning
- platform
- pytorch
+515 stars
from 25,044 · score 6.25
157.languagetool-org / languagetool
Style and Grammar Checker for 25+ Languages
- grammar
- natural-language
- natural-language-processing
- style-checker
- proofreading
- spellcheck
+513 stars
from 14,718 · score 6.24
158.facebookresearch / sam2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+510 stars
from 19,587 · score 6.24
+510 stars
from 15,070 · score 6.24
160.skfolio / skfolio
Python library for portfolio optimization, factor model construction, and risk management built on scikit-learn
- asset-allocation
- portfolio
- portfolio-optimization
- quantitative-finance
- risk-parity
- scikit-learn
- +9 more
+510 stars
from 2,076 · score 6.24
161.coqui-ai / TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
- python
- text-to-speech
- deep-learning
- speech
- pytorch
- tts
- +13 more
+508 stars
from 45,671 · score 6.23
162.SWivid / F5-TTS
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
+499 stars
from 15,008 · score 6.21
+497 stars
from 20,775 · score 6.21
164.microsoft / OmniParser
A simple screen parsing tool towards pure vision based GUI agent
+487 stars
from 25,118 · score 6.19
165.off-grid-ai / OGAM
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
- privacy-first
- gguf
- llama-cpp
- local-ai
- edge-ai
- offline-llm
- +14 more
+482 stars
from 2,839 · score 6.18
166.rerun-io / rerun
Visualize, query, and stream to train on multimodal robotics data.
- visualization
- computer-vision
- python
- robotics
- rust
- multimodal
- +1 more
+470 stars
from 11,219 · score 6.15
167.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
+455 stars
from 10,178 · score 6.12
168.theagentrouter / agent-router
Manages Unified Access to Generative AI Services built on Envoy Gateway
- ai
- ai-gateway
- api-gateway
- kubernetes
- llm
- inference
- +2 more
+455 stars
from 1,885 · score 6.12
169.2noise / ChatTTS
A generative speech model for daily dialogue.
- agent
- text-to-speech
- chat
- chatgpt
- chattts
- chinese
- +11 more
+448 stars
from 39,527 · score 6.11
170.facebookresearch / vggt
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
+445 stars
from 14,148 · score 6.10
171.optuna / optuna
A hyperparameter optimization framework
- python
- machine-learning
- parallel
- distributed
- hyperparameter-optimization
+440 stars
from 14,567 · score 6.09
172.esimov / caire
Content aware image resize library
- seam-carving
- image-processing
- image-resize
- edge-detection
- golang
- face-detection
- +4 more
+439 stars
from 10,439 · score 6.09
173.datalab-to / surya
OCR, layout analysis, reading order, table recognition in 90+ languages
+435 stars
from 21,143 · score 6.08
174.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
+428 stars
from 23,595 · score 6.06
175.lutzroeder / netron
Visualizer for neural network, deep learning and machine learning models
- neural-network
- deep-learning
- machine-learning
- deeplearning
- machinelearning
- ai
- +10 more
+425 stars
from 33,225 · score 6.05
176.onnx / onnx
Open standard for machine learning interoperability
+422 stars
from 21,215 · score 6.05
177.sml2h3 / ddddocr
TranslatedDaidai Didi (带带弟弟, "take little brother along") general-purpose captcha recognition OCR, PyPI version
+402 stars
from 14,498 · score 6.00
178.axolotl-ai-cloud / axolotl
Go ahead and axolotl questions
+386 stars
from 12,278 · score 5.96
179.roflcoopter / viseron
Self-hosted, local only NVR and AI Computer Vision software. With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.
- nvr
- network-video-capture
- network-video-recorder
- tensorflow
- darknet
- yolo
- +14 more
+378 stars
from 3,303 · score 5.94
180.facebookresearch / detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
+375 stars
from 34,590 · score 5.93
+374 stars
from 11,759 · score 5.93
182.Tencent-Hunyuan / HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
- video-generation
- diffusion-models
- diffusion-transformer
+367 stars
from 12,351 · score 5.91
183.zyddnys / manga-image-translator
TranslatedTranslate manga/image: one-click translation of text in all kinds of images https://cotrans.touhou.ai/ (no longer working)
- manga
- anime
- ocr
- deep-learning
- image-processing
- auto-translation
- +9 more
+364 stars
from 10,206 · score 5.90
184.karpathy / minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
+363 stars
from 10,642 · score 5.90
185.pot-app / pot-desktopArchived
Translated🌈 A cross-platform software for text translation and recognition.
- translation
- pot
- tauri
- translate
- pot-app
- ocr
- +5 more
+362 stars
from 18,980 · score 5.89
186.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
+360 stars
from 28,581 · score 5.89
187.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
+353 stars
from 59,871 · score 5.87
188.mlc-ai / mlc-llm
Universal LLM Deployment Engine with ML Compilation
- llm
- machine-learning-compilation
- language-model
- tvm
+353 stars
from 22,948 · score 5.87
189.huggingface / datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
+352 stars
from 21,758 · score 5.87
190.DLR-RM / stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
- reinforcement-learning
- reinforcement-learning-algorithms
- machine-learning
- gym
- openai
- baselines
- +8 more
+350 stars
from 13,608 · score 5.86
191.ageitgey / face_recognition
The world's simplest facial recognition api for Python and the command line
- machine-learning
- face-detection
- face-recognition
- python
+346 stars
from 56,519 · score 5.85
192.JaidedAI / EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
- ocr
- deep-learning
- crnn
- pytorch
- lstm
- machine-learning
- +9 more
+340 stars
from 29,781 · score 5.83
193.JabRef / jabref
Desktop app for managing BibTeX and BibLaTeX (.bib) libraries
- jabref
- bibtex
- java
- latex
- biblatex
- bibliography
- +14 more
+339 stars
from 4,527 · score 5.83
194.wandb / openui
OpenUI let's you describe UI using your imagination, then see it rendered live.
- ai
- generative-ai
- html-css-javascript
- tailwindcss
+334 stars
from 22,393 · score 5.81
195.facebookresearch / dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
+334 stars
from 13,162 · score 5.81
+330 stars
from 18,640 · score 5.80
197.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
+329 stars
from 18,618 · score 5.80
+324 stars
from 8,397 · score 5.78
199.voxel51 / fiftyone
Refine high-quality datasets and visual AI models
+321 stars
from 10,951 · score 5.77
200.karpathy / minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
+316 stars
from 24,680 · score 5.76