Trending Projects

A developer-focused platform for text-to-speech, RAG, and LLMs, with local-first architecture.

DeepSeekMoE is a novel Mixture-of-Experts language model framework for building highly specialized AI coding assistants.

The Alan AI SDK for iOS enables developers to add voice AI and conversational interfaces to their mobile apps.

A collection of high-impact and state-of-the-art single image super-resolution methods.

Compares the performance of multiple NVIDIA GPUs and Apple Silicon for running large language model inference.

A Python extension for the Stable Diffusion AI model, focused on the DreamBooth fine-tuning technique.

A benchmarking tool for evaluating the performance of popular machine learning algorithms and libraries.

Minimal, clean example of LSTM neural network training in Python for learning purposes.

A PyTorch implementation of accurate 3D face reconstruction from single images or image sets.

Chai-1 is a state-of-the-art model for biomolecular structure prediction, built with Python.

A curated list of papers about using deep learning for protein design.

A Python library for alpha matting, which is the process of extracting a foreground object from an image.

Recipes for shrinking, optimizing, and customizing cutting-edge computer vision models.

This is a PyTorch implementation of ArcFace, a deep learning-based face recognition algorithm.

A powerful multimodal transformer for combining language, vision, and other modalities in AI applications.

CenterNet is a Python library for object detection using keypoint triplets, with applications in computer vision.

A C++ library for 3D point cloud processing and visualization, with applications in self-driving cars and robotics.

A deep learning package for many-body potential energy representation and molecular dynamics

A PyTorch implementation of the InsightFace face recognition model.

Serverless AI agent framework with geo-distributed edge AI infrastructure for low-latency real-time applications.

A high-fidelity 3D creation tool from a single image using diffusion models for vibe coders.

A library focused on generating realistic talking head videos from images, useful for AI-powered avatar and animation projects.

Automatically visualize any dataset, any size with a single line of code, built for vibe coders.

Conditional Transformer Language Model for Controllable Text Generation

Official implementation of the PVT (Pyramid Vision Transformer) series, a backbone model for detection and segmentation tasks.

An Android application for super-resolution and image interpolation using popular AI models like RealSR, SRMD, and Waifu2x.

MotionGPT is a unified motion-language generation model that can generate human motion using large language models.

AIMedia is an AI-powered content creation and publishing platform for popular social media channels.

Python bindings for Transformer models implemented in C/C++ using the GGML library.

Official implementation of a decomposable multiscale mixing model for time series forecasting

CAM is a MATLAB library for generating Class Activation Maps, a technique for visualizing what a deep learning model focuses on.

A Python library for learning the fundamentals of machine learning and deep learning from scratch.

A Python library for deep and online learning with spiking neural networks (SNNs) using PyTorch.

An open-source humanoid arm for physical AI research and deployment in contact-rich environments.

A TensorFlow template application for building deep learning models and deploying them to production.

Petastorm enables training and evaluation of deep learning models from Apache Parquet datasets.

Efficient AI model training on medical images using any deep learning framework.

A real-time speech enhancement model that runs on a laptop CPU, useful for AI audio processing.

A curated list of open-source quantum software projects for developers working in quantum computing.

A Python library for computing BERT-based text generation evaluation metrics.

An open-ended evolution system for self-improving AI agents that can be used for developing advanced AI applications.

Flux 2 is a pure C inference engine for an image generation model, useful for vibe coders working with AI tools.

A curated reading list for security, safety, and privacy of large language models (LLMs) and AI systems.

Text Generator is an Obsidian plugin that allows you to generate text content using various AI providers.

A comprehensive survey of self-evolving AI agents, bridging foundation models and lifelong agentic systems.

An open-source toolbox for action understanding based on PyTorch, focused on computer vision and video analysis.

Official inference repo for FLUX.2 models, a library for building AI-powered applications.

A platform for designing and evaluating Graph Neural Networks (GNNs) using Python.

A Python library for creating invisible watermarks on images, useful for protecting digital content.

A collection of programming projects and tutorials for developers looking to build with AI tools.