Trending Projects

A Python library for creating video-based multimodal explanations for LLM theorem understanding.

A comprehensive collection of papers and resources related to image quality assessment (IQA) for developers.

Moonlight Documentation, a resource for developers building with AI tools and technologies.

A course that explores the intersection of philosophy and AI, with a focus on agent-based simulations.

A complete framework for Godot to create beautiful and complex AI motion for 2D and 3D game development.

This Python library provides tools for working with the CMeKG knowledge graph.

This project is a PyTorch implementation of diffusion models, a powerful generative AI technique.

A C++ implementation of Halcon's shape-based matching algorithm for computer vision applications.

An open-source robotics operating system (ROS) with support for speech recognition, semantic understanding, visual control, and Gazebo simulation.

An open-source marketing mix modeling library that uses AI/ML to democratize modeling knowledge and reduce human bias.

An open-source 6DoF head tracking software for gaming, simulations, and virtual experiences.

A comprehensive implementation of all reinforcement learning algorithms in a simpler way.

An AI-powered assistant that generates PowerPoint presentations from natural language prompts.

A Persian natural language processing toolkit for tasks like tokenization, lemmatization, and part-of-speech tagging.

Chainlit's cookbook repo provides a collection of Python scripts and examples for building AI-powered applications.

Generate music based on natural language prompts using local LLM models.

Pre-trained model for pitch estimation from audio, useful for music information retrieval tasks.

Synchronized Translation for Videos: Automatic dubbing and subtitling for video content.

Official PyTorch implementation of a framework for learning to adapt models at test time.

An AI-powered markdown editor that lets developers leverage large language models with their documents, deployable locally or in the cloud.

A one-click deployment solution to create a personal ChatGPT mirror site

An open-source, flexible quadrotor simulator for developing and testing autonomous drone applications.

An open-source DevOps tool for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.

A curated list of awesome resources for model-based reinforcement learning.

A Python library for speech restoration, including tasks like declipping, denoising, and dereverberation.

A Python library that uses CLIP and MLP to predict the aesthetic score of images, useful for vibe coders.

ZeroSearch: A Python library that incentivizes the search capability of large language models without actually searching.

A web interface for chatting with local large language models (LLMs) using the ollama API.

Magenta Studio is a collection of music plugins built on Magenta's open source AI tools and models.

A Jupyter Notebook repository that provides a function calling interface for developers working with AI tools.

EvTexture is an event-driven video super-resolution library for enhancing video quality using AI.

PyDMD is a Python library for dynamic mode decomposition, a data-driven method for model reduction.

PantoMatrix is a Python library for generating facial and body animations from speech, designed for vibe coders building AI-powered projects.

A search-enhanced large language model toolkit for building AI-powered applications and tools.

Provides ComfyUI nodes to use the Segment Anything Model for advanced image segmentation.

Crocoddyl is an optimal control library for robot control under contact sequence, focused on legged robotics and motion planning.

Prompty is a Python library that makes it easy to create, manage, debug, and evaluate LLM prompts for AI applications.

An all-in-one data labeling and annotation platform for multimodal data training, supporting 3D LiDAR, images, and language models.

An Azure-based Retrieval-Augmented Generation (RAG) pattern using Azure Cognitive Search and Azure OpenAI for ChatGPT-style experiences.

AirSLAM is a C++ library for real-time SLAM (Simultaneous Localization and Mapping) using visual-inertial odometry and 3D reconstruction.

An open-source library for object tracking using YOLOv8 and DeepSORT algorithms, suitable for vehicle counting and speed estimation applications.

Point-LIO is a C++ library for robust and accurate LiDAR-Inertial Odometry, a key technology for autonomous navigation.

A curated collection of must-read papers and blogs on speculative decoding techniques for developers.

Brian is a free, open-source simulator for spiking neural networks, used in computational neuroscience.

A multi-modal and multi-scenario dataset for ground robots research and SLAM applications.

A high-performance and lightweight PyTorch-based license plate recognition framework.

Open-source knowledge graph with 140M+ entities and relationships, useful for AI and data-driven applications.

Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation.

A project that bridges the gap between large language models (LLMs) and recommender systems.

A repository containing diagrams for visualizing neural network architectures, useful for AI/ML developers.