Trending Projects

An open-source question-answering tool that leverages large language models to provide answers to any query.

SadTalker is a CVPR 2023 project that enables stylized audio-driven single image talking face animation.

A nearly-live implementation of OpenAI's Whisper, a powerful speech recognition and translation tool.

Distributed GPU-accelerated framework for evolutionary computation and optimization algorithms.

A robotics simulation platform for training generalist robots on everyday tasks.

A GPU-optimized version of the MuJoCo physics simulator designed for NVIDIA hardware.

MSF is a modular framework for multi-sensor fusion based on an Extended Kalman Filter, useful for robotics and computer vision applications.

A companion website to the book 'Mathematics For Machine Learning'.

A community-driven AI automation framework that combines language models with specialized tools for tasks like web search, crawling, and Python code execution.

A system for agentic LLM-powered data processing and ETL workflows for unstructured data analysis.

An implementation of Graph Transformer Networks, a neural network architecture for graph-structured data.

A collection of research papers and resources on computer vision tasks like image classification, object detection, and face recognition.

A Python library for solving and discovering nonlinear partial differential equations using physics-informed neural networks.

Colossal-AI optimizes large AI model training and inference with distributed computing and GPU acceleration.

An offline Android SDK for face recognition, liveness detection, and 1:N & M:N face search

Moshi is an open-source speech-to-text foundation model and dialogue framework for building AI-powered voice apps.

Build, enrich, and transform datasets using AI models with no code

A pipeline parallel training script for diffusion models, useful for AI and machine learning researchers.

3D Point Cloud Annotation Platform for Autonomous Driving

An open-source GPU-accelerated robotics simulator and benchmark for manipulation skill learning.

A vision agent library for building AI-powered computer vision applications in Python.

Official implementation of a paper on VACE, a video creation and editing tool powered by AI.

An open-source large-scale manipulation platform for scalable and intelligent robotic systems.

AI-powered GitLab code review tool with code analysis, visualization, and messaging integrations.

An open-source TypeScript library that provides a wallet-like interface for managing AI agents and their resources.

A tutorial and code repository for using the Hugging Face Transformers library for NLP tasks.

Efficient multi-head latent attention kernels for AI coding tools and frameworks.

AI-powered note-taking and knowledge management for developers, with intelligent connections and ChatGPT integration.

RamaLama simplifies local serving of AI models and enables their use for inference in production via containers.

EverMemOS is an open-source, enterprise-grade intelligent memory system for AI-powered conversational applications.

Open-source browser automation library for AI agents to interact with web applications.

An AI inference operator for Kubernetes that makes it easy to serve ML models in production.

A general SLAM framework supporting different sensors and methods for 3D reconstruction and localization.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

AudioX is a Python library for audio processing and machine learning, designed for vibe coders.

A curated collection of high-quality models for the MuJoCo physics engine, useful for robotics and AI research.

FastAPI wrapper for Grok AI with streaming, image generation, and load balancing

Implementation of the state-of-the-art YOLOv13 object detection model with hypergraph-enhanced visual perception.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Minimal and annotated implementations of key ideas from modern deep learning research.

A Python library for embeddings and similarity search, potentially useful for AI coding tools and agents.

This is a curriculum for learning Natural Language Processing (NLP) from Siraj Raval's YouTube channel.

A tutorial series for developers to learn how to use large language models (LLMs) from zero to hero.

Bullet Physics SDK is a real-time collision detection and multi-physics simulation library for VR, games, robotics and more.

A curated collection of papers on generative information extraction using large language models.

A PyTorch library for building CNN-based text classification models.

Hackable and optimized Transformer building blocks for AI coding tools and libraries.

A collection of examples demonstrating the usage of the MLX framework for building AI-powered applications.

Safe Rust wrapper around the CUDA toolkit for GPU acceleration in AI/ML applications.

An AI observability platform for production LLM and agent systems, built with Python and Pydantic.