Trending Projects

Automatic feature extraction from time series data for data science and machine learning applications.

An open-source toolbox for image and video restoration tasks like super-resolution, denoising, and deblurring.

An agent framework for fintech and banks, with support for AI tools like OpenAI and LLMs.

Automagically synchronize subtitles with video using audio alignment and speech detection.

A collection of cheatsheets for the Stanford CS 230 Deep Learning course, covering key concepts and techniques.

A collection of reusable Python modules for building AI-powered applications and tools.

LIO-SAM is a tightly-coupled lidar-inertial odometry and mapping system for robot navigation.

InstantMesh is an efficient 3D mesh generation tool that can create high-quality 3D meshes from a single image.

A Python library for reinforcement learning tuning of large language model agents.

A modern Anki addon that implements the Free Spaced Repetition Scheduler algorithm for intelligent tutoring systems.

A Python library for evaluating the capabilities of large language models trained on code.

A library that redefines the regression task of DETRs as a fine-grained distribution refinement problem, with potential applications in object detection.

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

An AI-powered security toolkit for LLM vulnerability scanning and red teaming.

A Python library to track and report carbon emissions from computational workloads.

The official implementation of RAPTOR, a framework for Recursive Abstractive Processing for Tree-Organized Retrieval.

A research paper on representation alignment for training diffusion models for AI-assisted code generation.

A Python-based OCR (Optical Character Recognition) library for Tencent Hunyuan, a vibe coder's AI-powered developer platform.

Build an email assistant with human-in-the-loop and memory using the LangChain framework.

A high-performance Rust-based inference engine for deploying AI models in production.

An on-device GUI agent for operating Android apps, enhancing reasoning ability for efficient task execution.

A Python library that uses LLMs, computer vision, and speech recognition to analyze video content.

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

A web app that uses AI to index videos, enable semantic search, and export scenes for developers building with AI tools.

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

Singing Voice Conversion framework using AI

PaddleDetection is an open-source object detection toolkit based on the PaddlePaddle deep learning framework, supporting various computer vision tasks.

High-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

Gorilla is a Python tool for training and evaluating large language models (LLMs) for API/function calls.

Point Cloud Library (PCL) is a powerful open-source library for 3D computer vision and point cloud processing.

A set of containers for running machine learning models and applications on various ML frameworks.

A collection of PyTorch tutorials for developers to learn and practice AI/ML with Python.

A powerful multi-object tracking library with modular SOTA tracking modules for segmentation, detection, and pose estimation.

A feature-rich GPT wrapper for Git that generates commit messages with an LLM in 1 second, supporting various providers and local models.

AI suite with advanced AI/AGI functions, including personas, multi-model chats, text-to-image, voice, and more.

A high-performance GPU-accelerated fluid dynamics simulation library for scientific computing and visualization.

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

A unified, comprehensive and efficient recommendation library for building recommendation systems.

DeepSeekMath is a Python library that pushes the limits of mathematical reasoning in open language models.

A comprehensive robotics toolbox for Python with tools for kinematics, dynamics, motion planning, and more.

Multimodal conversational video generation powered by AI, enabling new vibe-coder collaboration experiences.

Code for running RFdiffusion, a machine learning library for protein structure prediction.

Curated list of resources for building autonomous vehicles and self-driving car technology

An automated translation solution for visual novels (Galgames) that supports major language models like GPT-4 and Claude.

A collection of examples and demos for the Transformers.js library, which brings powerful AI models to JavaScript.

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

Simple, hackable offline speech-to-text tool using the VOSK-API, useful for vibe coders building AI apps.

Official repository of Point Transformer V3 (PTv3), a computer vision AI model for point cloud processing.

A Go-based command-line tool for managing Ollama LLM models on Linux and macOS.

This is a Jupyter Notebook repository for an open-source embodiment project from Google DeepMind.