Trending Projects

An open-source collection of computer vision tutorials and resources for developers.

Jlama is a modern LLM inference engine for Java, enabling vibe coders to build AI-powered applications.

A Home Assistant integration and model to control your smart home using a local large language model.

A deep reinforcement learning project for mobile robot navigation in a Gazebo simulator using the ROS framework.

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

A robust, efficient, and adaptable toolkit for segmenting text into sentences or other semantic units.

A library for training sparse autoencoders on language models, potentially useful for vibe coders.

Autogenerate subtitles for media using the OpenAI Whisper model, integrated with popular media servers.

A Python client for Qdrant, a powerful vector search engine for building AI-powered applications.

A Scala-based hardware accelerator for deep neural networks, part of Berkeley's AI hardware research.

A collection of novel jailbreak methods for large language models (LLMs) focused on privacy and safety.

Objaverse-XL is a massive 3D object dataset with APIs for downloading and processing the data, useful for computer vision and 3D modeling projects.

An open-source, feature-rich web UI for image matching and visual localization tasks using AI models like SIFT, SuperPoint, and SuperGlue.

A Python library for building AI-powered applications, with support for various AI models and tools.

SMAC3 is a versatile Bayesian optimization package for hyperparameter optimization in machine learning models.

A Rust library that helps developers work with AI models more reliably and persistently.

LPCNet is an efficient neural speech synthesis library for developers building voice-based applications.

A high-performance, end-to-end deep learning-based captcha recognition model for developers.

Fine-tune and deploy the Whisper speech recognition model with accelerated inference and support for various platforms.

Detoxify is a Python library with trained models to detect toxic comments, built using Pytorch Lightning and Transformers.

A Python library for spatio-temporal graph convolutional networks, a type of graph neural network for modeling graph-structured data.

A minimal tensor processing unit (TPU) for AI and machine learning workloads, inspired by Google's TPU V2 and V1.

An implementation of the Attention Is All You Need paper, built with PyTorch and Jupyter Notebooks.

Reverse-engineered API for the Alibaba Tongyi Qwen 2.5 large language model, providing AI capabilities like image generation, document analysis, and conversational AI.

Highly performant, modular, and production-ready inference, ingestion, and indexing library built in Rust for AI-powered applications.

A collection of research papers on autonomous agents and large language models (LLMs) updated daily.

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

This Java repository provides examples of using Spring for AI-related development.

A comprehensive survey of deep learning-based image fusion techniques for computer vision applications.

Official code and checkpoint release for mobile robot foundation models like GNM, ViNT, and NoMaD.

A curated list of resources for building multi-modal GUI agents using large language models.

A frontier multimodal foundation model for advanced image and video understanding tasks.

A GPU-accelerated TSDF and ESDF library for robots equipped with RGB-D cameras.

An async RL training library for scaling AI model training and deployment.

Open Images is a large dataset of annotated images for computer vision and machine learning research.

A unified framework for efficient fine-tuning and retrieval augmented generation (RAG) using LLMs.

A tool for creating comics using AI, supporting script writing, storyboarding, and character style control.

GMTalker is a 3D digital human system that integrates speech recognition, speech synthesis, natural language understanding, and mouth animation for fast deployment on Windows, Linux, and Android.

A deep reinforcement learning library for training robotic agents to plan pushing and grasping actions for manipulation tasks.

VideoMamba is a state space model for efficient video understanding, focused on AI and machine learning.

A medical Q&A system built with RAG and large language models, leveraging knowledge graphs and NLP to provide reliable medical advice.

A PyTorch implementation of the Mean Flows for One-step Generative Modeling paper, for vibe coders building AI tools.

A Python library for depth estimation and 3D/4D reconstruction using AI-powered prompts.

A Python library for training a humanoid robot to walk using reinforcement learning.

A Python GUI tool for offline transcription of speech recordings, including speaker diarization, using state-of-the-art machine learning models.

RAGChecker is a fine-grained framework for diagnosing RAG (Retrieval-Augmented Generation) models.

RTP-LLM is a high-performance LLM inference engine from Alibaba for diverse AI applications.

Inference code and configs for the ReplitLM model family, a large language model for AI-powered coding assistants.

A Python library that provides a wrapper around various speech quality metrics for audio processing and analysis.

An end-to-end web agent built with large multimodal models, enabling AI-powered web browsing and automation.