Trending Projects

An open-source AI platform for training and deploying AI agents for StarCraft II, with distributed training and grandmaster-level performance.

Multiversal tree writing interface for human-AI collaboration on creative coding projects.

A comprehensive collection of resources and examples related to chatbots and conversational AI applications.

A realtime serving engine for Data-Intensive Generative AI Applications built in Rust.

Risuai is a user-friendly software for LLM roleplaying, allowing developers to create their own stories and AI-driven characters.

This handbook provides practical guidance for researchers and practitioners on the latest Text-to-SQL techniques.

A Python library for 3D human avatar reconstruction from videos using self-supervised scene decomposition.

Attention-based model for learning to solve different routing problems, useful for AI coding tools.

PhysGaussian is a physics-integrated 3D Gaussian generative dynamics library for CVPR 2024.

An open-source AI-powered computer vision model for object detection, segmentation, and understanding.

A Python library for detecting and analyzing comparisons to ChatGPT in text, with a corpus of human-written comparisons.

An R library for using the TensorFlow machine learning framework, enabling vibe coders to build AI-powered applications.

A Python library for unsupervised time series anomaly detection, useful for data science and ML applications.

A Python library for automatically generating high-quality prompts for large language models.

An imitation learning benchmark for complex locomotion tasks using the MuJoCo physics simulation engine.

A benchmark for measuring the performance of AI agents at machine learning engineering tasks.

This repository contains the source code for a semantic image segmentation method using Conditional Random Fields as Recurrent Neural Networks.

Scalable, memory-optimized training of diffusion models for AI-powered applications.

Official codebase for OMG-LLaVA and OMG-Seg, state-of-the-art computer vision models presented at CVPR-24 and NeurIPS-24.

QuantAgent is an official repository for a platform that enables developers to build AI-powered applications.

A curated list of Embodied AI/Robotics job opportunities for developers interested in building AI-powered robots and agents.

All-in-one training for vision models with pretraining, fine-tuning, and distillation capabilities.

AudioMuse-AI is an open-source Docker-based environment that generates playlists using AI audio analysis.

OKVIS is an open-source library for visual-inertial SLAM, enabling real-time 3D reconstruction from camera and IMU data.

Official implementation of X-Decoder, a generalized decoding model for pixel, image, and language tasks.

A collection of recent Transformer-based computer vision and related research papers.

A curated list of accepted papers from various AI, ML, and robotics conferences.

An unofficial Python wrapper for the OpenAI ChatGPT API, enabling developers to integrate ChatGPT functionality into their applications.

This is a Python 3 implementation of the examples from the book 'Machine Learning in Action'.

A strong and open-source vision language assistant for mobile devices, leveraging the power of AI.

An industrial-grade graph neural network framework for building large-scale graph-based AI applications.

An open-source platform for building and managing AI-optimized context graphs for AI-powered applications.

Official implementation of a paper on estimating geometry in the presence of motion, likely useful for computer vision and 3D applications.

A flexible and powerful monitoring system for vibe coders to monitor their AI-powered applications.

A translation of Andrew Ng's book 'Machine Learning Yearning' for developers interested in machine learning.

A tool that helps developers easily share ChatGPT Plus/Claude Pro services with their peers.

A reactive runtime for building durable AI agents using Rust, with a focus on LLM orchestration and debugging.

ReCall is a library for training large language models (LLMs) to reason and use tools via reinforcement learning.

A secure, production-ready Angular/ASP.NET Core template for building AI-powered web applications

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

A free and open-source tool that converts images to 3D parallax effect videos using AI depth estimation.

A versatile diffusion model for text, image, and variation generation in a single model.

This repository provides a tutorial on using chatGPT, prompts, and large language models (LLMs) for developers.

Modular deep reinforcement learning framework in PyTorch for building AI-powered applications.

A Python library for 6-DoF tracking and 3D reconstruction of unknown objects using neural networks.

An elegant PyTorch implementation of popular transformer models like BERT, GPT, and more for NLP tasks.

A deep learning-based face detection and recognition library implemented in PyTorch for developers working with computer vision.

GoMLX is an accelerated machine learning framework for Go, enabling high-performance AI/ML development.

This repository provides an official implementation of a CVPR 2023 paper on handwriting generation using disentangled AI models.

PyTorch implementation of state-of-the-art reinforcement learning algorithms for vibe coders.