Trending Projects

A Rust library for blazingly fast LLM inference, useful for AI coding and ML applications.

This project aims to speed up large language model (LLM) inference and enhance their understanding of key information through prompt and KV-Cache compression.

A production-ready multi-agent orchestration framework for building AI-powered applications and workflows.

A library for creating lip-synced videos using Stable Diffusion, focused on research and virtual avatars.

MuseTalk is a Python library for real-time, high-quality lip synchronization using latent space inpainting.

An open-source project that provides a state-of-the-art image restoration model using the Swin Transformer architecture.

This repo contains a course on Deep Reinforcement Learning from Hugging Face.

An advanced real-time screen translator for games, videos, and static text, powered by machine learning.

AIGCPanel is an all-in-one AI digital human system that simplifies local model management, import, and use.

A Python and OpenCV-based scene cut/transition detection library for video processing.

A machine learning-powered image inpainting tool that can remove watermarks from images.

LightGlue is a high-performance local feature matching library for computer vision tasks like pose estimation.

A collection of example workflows for the ComfyUI AI tool, which allows developers to create custom AI models and applications.

This repository provides examples and tutorials to help developers build AI systems using popular AI tools and frameworks.

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

This is Anthropic's original performance take-home, now open for developers to try out AI tools and technologies.

Grounded SAM 2 is an open-source library for ground and track anything in videos using state-of-the-art AI models.

Waymo Open Dataset is a large-scale dataset for autonomous driving research and development.

A library of tile primitives for building speedy CUDA kernels, useful for vibe coders working on AI tools.

A comprehensive collection of interview questions and answers for AI, computer vision, and LLM topics.

Laminar is an open-source observability platform purpose-built for AI agents and workflows.

An awesome list for Whisper, an open-source AI-powered speech recognition system by OpenAI.

A TypeScript plugin for monitoring Google Antigravity AI model quotas and usage.

Official SeedVR2 Video Upscaler for ComfyUI, a Python-based AI coding tool for vibe coders.

A collection of Jupyter Notebook codes and tutorials for a variety of AI projects and data science tasks.

An NCNN-based implementation of Real-ESRGAN, a practical algorithm for general image restoration and super-resolution.

A production-ready FastAPI template for building scalable, secure, and maintainable AI agent services with LangGraph integration.

A Python library that can generate videos from images at any resolution using a flexible framework.

This repository provides a collection of MATLAB and Simulink project ideas to help developers gain practical experience in AI, robotics, and more.

Official PyTorch implementation of a diffusion transformer model with representation autoencoders for AI-assisted coding.

AI-powered PowerPoint presentation generation tool that supports complex features like charts, animations, and 3D effects.

Self-learning data agent with 6-layer context grounding for autonomous data analysis and reasoning.

MAI-UI is a Jupyter Notebook-based platform for building real-world centric GUI agents powered by large language models.

Qwen-Image-Layered is a Python library for layered decomposition and inherent editability of images.

A Rust library for running customized and fine-tuned large language models (LLMs) locally or on the edge.

An index of the LangChain + LangGraph ecosystem for building LLM and multi-agent applications.

A Java library that provides a set of examples for using the LangChain framework, which helps build applications with large language models.

Custom UI for the LangChain AI agent framework, focused on building AI-powered applications.

A small, lightweight tensor library in C for developers working on AI/ML projects.

Tools for training and deploying reinforcement learning models on the Unitree Go1 robot in a sim-to-real setting.

A Python library that enables training powerful AI agents using end-to-end reinforcement learning.

AgentEvolver is a Python library for building self-evolving agent systems powered by large language models and reinforcement learning.

A Python library for building generative social simulations with multi-agent interactions.

A next-generation object detection model that can detect anything with high accuracy and efficiency.

A comprehensive collection of SLAM (Simultaneous Localization and Mapping) applications and comparisons for robotics and lidar-based navigation.

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

Open-source Grok-1 model for local inference with JAX

BERT - Pre-trained NLP models and TensorFlow code for natural language understanding

Reinforcement learning toolkit for developing and comparing algorithms.

Configure and deploy autonomous AI agents in browser