Ranked by Attention Score: stars gained over the last 7 complete days
401–500 of 837 by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Hierarchical Reasoning Model Official Release
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Implementation of Nougat Neural Optical Understanding for Academic Documents
NSFW detection on the client-side via TensorFlow.js
NVIDIA cuML: GPU-Accelerated Machine Learning
3D Computer Vision Framework
Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.
Give a face to your voice AI in 5 lines of code. Generate realtime avatar video connected to your voice AI locally
Official code for Agent-Reflex: Teaching Language Agents to Act Reflectively
SteerAct: Unlocking Action Models through Few-Shot Temporal Steering
Foundational Models for State-of-the-Art Speech and Text Translation
Low-code framework for building custom LLMs, neural networks, and other AI models
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
Visual localization made easy with hloc
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.
Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Live Helper Chat - live support for your website. Featuring web and mobile apps, Voice & Video & ScreenShare. Supports Telegram, Twilio (whatsapp), Facebook messenger including building a bot.
Reinforcement Learning environments based on the 1993 game Doom :godmode:
[Tech Report] Simplifying and Improving On-Policy Distillation for Few-step Diffusion
Graph Neural Network Library for PyTorch
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
NLTK Source
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
QLoRA: Efficient Finetuning of Quantized LLMs
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
An open source python library for automated feature engineering
Flax is a neural network library for JAX that is designed for flexibility.
Fit interpretable models. Explain blackbox machine learning.
An open-source read-along document reader server with high-quality TTS options, synchronized highlighting, and audiobook export for EPUB, PDF, DOCX, TXT, and MD.
Powerful, free, context-aware AI native meeting assistant that transcribes real-time and locally on your computer, writes the minutes, and lets your AI agent drive it.
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server
Deepfakes Software For All
The open-source hub to build & deploy GPT/LLM Agents ⚡️
Face recognition using Tensorflow
High-Resolution Image Synthesis with Latent Diffusion Models
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
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
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
OpenMMLab's next-generation platform for general 3D object detection.
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
Dataflow compiler for QNN inference on FPGAs
Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI applications inspired by Vercel AI SDK.
The UI SDK and agent-ready developer toolkit for AI factories, robotics, and autonomous vehicles.
Making large AI models cheaper, faster and more accessible
TranslatedChinese word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, constituency parsing, semantic dependency parsing, semantic role labeling, coreference resolution, style transfer, semantic similarity, new word discovery, keyword and keyphrase extraction, automatic summarization, text classification and clustering, pinyin and Simplified/Traditional Chinese conversion, natural language processing
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Pretrained models for TensorFlow.js
Python package built to ease deep learning on graph, on top of existing DL frameworks.
The repository host gives no description.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
OCR & Document Extraction using vision models
An elegant PyTorch deep reinforcement learning library.
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
Playing Pokemon Red with Reinforcement Learning
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
The Open Source Feature Store for AI/ML
An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
Uplift modeling and causal inference with machine learning algorithms
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
A python library for self-supervised learning and latent world models on images.
Copy any text on your screen, stop retyping.
An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.
GoMLX: An Accelerated Machine Learning Framework For Go
Brian is a free, open source simulator for spiking neural networks.
AI Skill for Playwright Best Practices—made by Currents.dev
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
Dadbod Grip turns database tables into editable Vim buffers, with schema browsing, staged mutations, generated SQL, relationship navigation, and cross-database federation inside Neovim.
High-performance Piecewise Geometric Model (PGM) learned index implementation in pure Rust with strict epsilon error guarantees
Manga / black & white comic filter for ComfyUI: crisp lines, flat tones, real screentone (halftone), solid blacks and panel frames.
Build RL environments for any domain from real cases that Browser Use agents mine from the web
Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your machine.
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
A WebGL accelerated JavaScript library for training and deploying ML models.
Instant neural graphics primitives: lightning fast NeRF and more
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
A toolkit for making real world machine learning and data analysis applications in C++
StyleGAN - Official TensorFlow Implementation
A reference containing Styles and Keywords that you can use with MidJourney AI. There are also pages showing resolution comparison, image weights, and much more!
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Implementation of Denoising Diffusion Probabilistic Model in Pytorch