1.heygen-com / hyperframes
Write HTML. Render video. Built for agents.
+21,893 stars
from 56,462 · score 9.99
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
1–100 of 317 by Attention Score · Oct 5, 2026 – Nov 3, 2026 (UTC)
2.NandhaKishorM / laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
- calibration
- classification
- decision-model
- huggingface
- jev
- modernbert
- +7 more
+4,403 stars
from 30,559 · score 8.39
3.OpenBMB / VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
- audio
- deeplearning
- minicpm
- python
- pytorch
- speech
- +8 more
+2,880 stars
from 38,125 · score 7.97
4.FlashML-org / FreeVideo
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
+1,969 stars
from 768 · score 7.59
5.huggingface / transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- nlp
- natural-language-processing
- pytorch
- pytorch-transformers
- transformer
- model-hub
- +13 more
+1,913 stars
from 166,592 · score 7.56
6.PaddlePaddle / PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
- pp-structure
- document-parsing
- +7 more
+1,736 stars
from 90,477 · score 7.46
7.leemysw / yovoice
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
- audio
- desktop-app
- macos
- text-to-speech
- tts
- voice
- +10 more
+1,708 stars
from 341 · score 7.44
8.krillinai / OpenCreator
Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.
- video-transcription
- video-translation
- dubbing
- localization
- tts
- agent-skills
- +6 more
+1,577 stars
from 12,555 · score 7.36
9.Robbyant / lingbot-map
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
+1,353 stars
from 17,181 · score 7.21
10.KittenML / KittenTTS
Open-source State-of-the-art TTS model which runs on a CPU 😻
+1,314 stars
from 15,471 · score 7.18
11.bilibili / Index-Translate
A Multilingual, Multimodal Translation Model Family
- llm
- machine-translation
+1,301 stars
from 616 · score 7.17
12.Automattic / harper
Offline, privacy-first grammar checker. Fast, open-source, Rust-powered
- developer-tools
- english-language
- grammar-checker
- rust
- webassembly
- chrome-extension
- +3 more
+1,297 stars
from 16,094 · score 7.17
13.ATH-MaaS / Pixelle-Video
Translated🚀 AI Fully Automated Short Video Engine
- aigc
- comfyui
- image-generation
- tts
- video-generation
+1,188 stars
from 28,547 · score 7.08
14.deepopen-com / deepopen
TranslatedNon-autoregressive System 1 decision engine, designed for structured, typed decision-making scenarios. DeepOpen Multilingual, non-autoregressive System 1 decision engine.
+1,095 stars
from 2,001 · score 7.00
15.tensorflow / tensorflow
An Open Source Machine Learning Framework for Everyone
+1,008 stars
from 200,282 · score 6.92
16.kornia / kornia
🐍 Geometric Computer Vision Library for Spatial AI
+912 stars
from 11,399 · score 6.82
+895 stars
from 61 · score 6.80
18.breezeblue-ai / breeze-tts
Official PyTorch inference for Breeze TTS 2
+891 stars
from 514 · score 6.79
19.ant-research / AntOmniEvo
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
- evolutionary-algorithms
- rsi-ai
- self-improvement
- llm-agent
- multi-agent
- automation
- +6 more
+882 stars
from 341 · score 6.78
+755 stars
from 1,578 · score 6.63
21.huggingface / lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
+754 stars
from 27,915 · score 6.63
+722 stars
from 1 · score 6.58
23.Evil0ctal / Douyin_TikTok_Download_API
TranslatedSelf-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.
- tiktok
- douyin
- scraper
- crawler
- web-scraping
- tiktok-scraper
- +14 more
+713 stars
from 20,421 · score 6.57
24.syv-ai / HyperQwen
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
- qwen
- qwen3
- +6 more
+678 stars
from 1,843 · score 6.52
+644 stars
from 17,703 · score 6.47
26.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
+625 stars
from 15,087 · score 6.44
+617 stars
from 33,424 · score 6.43
28.OpenBMB / MiniCPM-V
See, hear, and interact on your local devices.
- minicpm
- minicpm-v
- multi-modal
- minicpm-o
+596 stars
from 26,471 · score 6.39
29.QwenLM / Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
+583 stars
from 13,612 · score 6.37
30.srbhr / Resume-Matcher
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
- text-similarity
- natural-language-processing
- word-embeddings
- python
- machine-learning
- resume
- +8 more
+578 stars
from 28,527 · score 6.36
31.shanliuling / dsh-image-gen
TranslatedAI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
+572 stars
from 513 · score 6.35
32.tesseract-ocr / tesseract
Tesseract Open Source OCR Engine (main repository)
- tesseract
- tesseract-ocr
- ocr
- lstm
- machine-learning
- ocr-engine
- +1 more
+562 stars
from 76,762 · score 6.33
33.drowzeys / Imagination-Studio-by-keys-Wasserman
Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-K pictures and MiniMax H3 / FastH3 video with sound on TensorFold.
- apple-silicon
- minimax-h3
- mlx
- qwen-image
- tensorfold
- text-to-video
- +5 more
+551 stars
from 3 · score 6.31
34.AIMixer / ComfyUI_MiniMaxH3_Director
Multi-segment MiniMax H3 Director for official ComfyUI MiniMax-H3
+521 stars
from 2,161 · score 6.26
35.Huanshere / VideoLingo
TranslatedNetflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team
- ai-translation
- dubbing
- localization
- video-translation
- voice-cloning
+491 stars
from 18,564 · score 6.20
36.QwenAudio / CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
- audio-generation
- gpt-4o
- text-to-speech
- tts
- cantonese
- chatbot
- +13 more
+467 stars
from 23,800 · score 6.15
37.YaoFANGUK / video-subtitle-remover
TranslatedAI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures. It removes hard-coded subtitles and text watermarks from images/videos and generates subtitle-free, watermark-free image/video files at lossless resolution. No third-party API application is needed; it runs locally.
- ai
- deepleanring
- vsr
- sub-remove
- subtile
+448 stars
from 13,116 · score 6.11
38.opencv / opencv
Open Source Computer Vision Library
+445 stars
from 90,986 · score 6.10
39.Human-Agent-Society / reef
Infrastructure for continually self‑improving agents
+444 stars
from 7,346 · score 6.10
40.mlflow / mlflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
- machine-learning
- ai
- ml
- mlflow
- apache-spark
- model-management
- +12 more
+432 stars
from 28,222 · score 6.07
41.haolpku / Omni-Edu
OmniEdu: Open Foundation Models for Learning and Teaching
+426 stars
from 112 · score 6.06
42.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
+402 stars
from 37,137 · score 6.00
43.baidu-baige / LoongSage
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.
+327 stars
from 228 · score 5.79
44.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.
+310 stars
from 2,947 · score 5.74
45.groundingpi / GroundingPI
A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations.
- embodied-ai
- gui-grounding
- object-detection
- ocr
- physical-intelligence
- pointing
- +4 more
+303 stars
from 3 · score 5.72
+297 stars
from 17,077 · score 5.70
47.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
+296 stars
from 11,002 · score 5.69
48.datalab-to / chandra
OCR model that handles complex tables, forms, handwriting with full layout.
+283 stars
from 12,394 · score 5.65
49.google-research / google-research
Google Research
+262 stars
from 38,839 · score 5.57
50.modelscope / ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
+260 stars
from 15,770 · score 5.56
51.DrewThomasson / ebook2audiobook
Generate audiobooks from e-books, 50+ TTS engines with voice cloning and 1696 languages!
+254 stars
from 20,241 · score 5.54
52.Tencent / WeVisDoc
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
+249 stars
from 262 · score 5.52
53.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
+245 stars
from 28,376 · score 5.51
54.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
+237 stars
from 34,619 · score 5.47
55.yifanzhang-pro / recurrent-looped-tranformer
Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)
+235 stars
from 903 · score 5.46
56.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
+231 stars
from 15,998 · score 5.45
57.facebookresearch / detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
+225 stars
from 34,740 · score 5.42
58.jax-ml / jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
+223 stars
from 36,349 · score 5.41
59.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.
+193 stars
from 54,905 · score 5.27
60.wandb / openui
OpenUI let's you describe UI using your imagination, then see it rendered live.
- ai
- generative-ai
- html-css-javascript
- tailwindcss
+190 stars
from 22,537 · score 5.25
61.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
+190 stars
from 16,157 · score 5.25
62.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
+175 stars
from 10,936 · score 5.17
63.joonspk-research / generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
+170 stars
from 22,164 · score 5.14
64.thu-nics / AKV
Official implementation of paper "Cache Engineering for Agents"
+170 stars
from 1 · score 5.14
65.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.
+167 stars
from 19,930 · score 5.12
66.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
+162 stars
from 18,529 · score 5.09
67.rerun-io / rerun
Visualize, query, and stream to train on multimodal robotics data.
- visualization
- computer-vision
- python
- robotics
- rust
- multimodal
- +1 more
+162 stars
from 11,527 · score 5.09
+155 stars
from 21,117 · score 5.05
69.QwenLM / Qwen3-VL
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
+155 stars
from 20,009 · score 5.05
70.axolotl-ai-cloud / axolotl
Go ahead and axolotl questions
+154 stars
from 12,510 · score 5.04
71.datalab-to / surya
OCR, layout analysis, reading order, table recognition in 90+ languages
+151 stars
from 21,427 · score 5.02
72.modelscope / DiffSynth-Studio
Enjoy the magic of Diffusion models!
+149 stars
from 13,188 · score 5.01
73.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
+146 stars
from 21,849 · score 4.99
74.allenai / olmocr
Toolkit for linearizing PDFs for LLM datasets/training
+145 stars
from 19,668 · score 4.98
75.mlc-ai / web-llm
High-performance In-browser LLM Inference Engine
- deep-learning
- llm
- tvm
- webgpu
- webml
- chatgpt
- +1 more
+141 stars
from 19,212 · score 4.96
76.zai-org / CogVideo
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
- llm
- sora
- video-generation
- cogvideox
- image-to-video
- text-to-video
+140 stars
from 13,040 · score 4.95
77.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
+137 stars
from 43,153 · score 4.93
78.opencoredev / bg0
Private, unlimited background removal that runs in your browser.
+135 stars
from 353 · score 4.91
79.voxel51 / fiftyone
Refine high-quality datasets and visual AI models
+134 stars
from 11,138 · score 4.91
80.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
+126 stars
from 28,815 · score 4.84
81.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
+121 stars
from 11,090 · score 4.80
+120 stars
from 8,601 · score 4.80
83.mlc-ai / mlc-llm
Universal LLM Deployment Engine with ML Compilation
- llm
- machine-learning-compilation
- language-model
- tvm
+114 stars
from 23,187 · score 4.74
84.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
+111 stars
from 30,010 · score 4.72
85.nerfstudio-project / nerfstudio
A collaboration friendly studio for NeRFs
- nerf
- pytorch
- 3d
- 3d-graphics
- 3d-reconstruction
- computer-vision
- +4 more
+111 stars
from 12,033 · score 4.72
86.facebookresearch / dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
+110 stars
from 13,386 · score 4.71
+106 stars
from 17,236 · score 4.67
88.hpcaitech / Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
+104 stars
from 29,808 · score 4.65
+102 stars
from 18,868 · score 4.63
90.keras-team / keras
Deep Learning for humans
+101 stars
from 64,315 · score 4.62
91.IDEA-Research / GroundingDINO
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
- object-detection
- open-world
- open-world-detection
- vision-language
- vision-language-transformer
+99 stars
from 10,632 · score 4.61
92.huggingface / datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
+97 stars
from 22,013 · score 4.58
93.onnx / onnx
Open standard for machine learning interoperability
+97 stars
from 21,540 · score 4.58
94.huggingface / pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
- pytorch
- resnet
- pretrained-models
- pretrained-weights
- distributed-training
- mobile-deep-learning
- +14 more
+93 stars
from 37,169 · score 4.54
+90 stars
from 12,043 · score 4.51
96.OpenMOSS / MOSS
An open-source, tool-augmented conversational language model from Fudan University
- chatgpt
- deep-learning
- dialogue-systems
- large-language-models
- natural-language-processing
- text-generation
+88 stars
from 12,249 · score 4.49
97.google / magika
Fast and accurate AI powered file content types detection
- deep-learning
- filetype
- keras-classification-models
- keras-models
- mime-types
- ai
- +1 more
+87 stars
from 18,675 · score 4.48
98.alphacep / vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
- speech-recognition
- asr
- voice-recognition
- speech-to-text
- android
- ios
- +14 more
+86 stars
from 15,140 · score 4.47
99.Krusty84 / triton-ascend-agent-dev-kit
A toolkit for AI agents used for development on Triton-Ascend for Ascend NPU
- ai
- ascend
- ascend-npu
- npu
- triton
- triton-ascend
- +3 more
+86 stars
from 106 · score 4.47
100.n8n-io / self-hosted-ai-starter-kit
The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.
- ai
- low-code
- self-hosted
- starter-kit
- ai-agents
+80 stars
from 15,246 · score 4.39