Trending Projects

A fully-automated AI assistant that helps with deep research, powered by large language models.

SALMONN is a suite of advanced multi-modal large language models (LLMs) for audio, speech, and video understanding.

Cluely is an AI-powered desktop assistant that provides real-time insights and support during meetings, interviews, and professional conversations.

A Python library for connecting Gaussian splatting and depth in computer vision tasks like monocular depth estimation and view synthesis.

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

DeepEP is an efficient expert-parallel communication library for CUDA-based applications.

DeepSDF is a Python library for learning continuous signed distance functions for shape representation.

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

A novel Multimodal Large Language Model (MLLM) architecture for structurally aligning visual and textual embeddings.

Automatically generate YouTube subtitles using OpenAI's Whisper speech recognition model

End-to-end NLP workflows from prototype to production for vibe coders building AI-powered apps

A lightweight, open-source speech synthesis library written in C for embedded devices like the Commodore 64.

A unified deep learning model for correspondence, stereo, and depth estimation tasks.

A collection of n8n workflows, templates, AI automations, and AI agents for building AI-powered applications.

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

A privacy-focused middleware for AI-powered applications built on trusted execution environments like Intel SGX.

Agent Laboratory is an end-to-end autonomous research workflow to assist human researchers in implementing their ideas.

An open-source tool for labeling images and training computer vision models using a variety of popular detection models.

A scalable multimodal reasoning framework for AI-powered applications with a focus on video and image understanding.

Machine learning-powered implementation of the classic Flappy Bird game using neural networks and genetic algorithms.

This repository provides a real-time 4D view synthesis system that can generate 4K resolution outputs.

A curated collection of articles and resources on search, recommendation, and natural language processing.

A Python library that provides a unified interface for communicating with large language models (LLMs).

Efficient visual geometry learning for AI-powered applications with permutation-equivariant representations.

A large-scale LLM inference engine built in C++ with support for various AI hardware accelerators.

A Python-based assistant for reverse engineering and exploring the 1999 time period.

An open-source tool for quickly annotating and labeling images for computer vision and deep learning projects.

This repository contains a dataset and code for a study on using large language models for freelance software engineering.

Generate music based on natural language prompts using local LLM models.

This repository provides open-source code and educational resources for learning deep learning and machine learning with Python.

A library of prompts for AI-powered tools and applications, curated by the Cline community.

A flexible, extensible framework for gait recognition that allows designing and comparing models easily.

Taipy is a Python library that helps developers turn data and AI algorithms into production-ready web apps quickly.

An open-source implementation of GPT-2 and GPT-3-style language models using the mesh-tensorflow library.

Rust bindings for the C++ API of PyTorch, a popular deep learning and machine learning library.

A curated list of Large Language Model resources for training, serving, fine-tuning, and building LLM applications.

A Go library for generating high-quality triangulated and polygonal art from images using evolutionary algorithms.

Minimal implementations of basic reinforcement learning algorithms in PyTorch for educational purposes.

A Python library for parsing natural language text into grammatical structure.

Generate text images for training deep learning OCR models, a key tool for vibe coders working with AI-powered text recognition.

WebThinker is a powerful framework for building large language models with deep research capabilities.

An open-source Java toolkit for building, evaluating, and deploying sophisticated AI agents.

A Python library for learning and using OpenCV, a popular computer vision library.

Offline speech recognition for Android using the Vosk library, a popular open-source speech recognition toolkit.

Jupyter notebooks for Deep Learning with Python book code samples

Advanced AI Explainability library for computer vision models built with PyTorch.

A Python library for generating 3D models from text or images using NeRF and Stable Diffusion.

Zonos is an open-source, high-quality text-to-speech model for developers building AI-powered applications.

A roadmap to learn Generative AI tools and technologies in 2025

Edward is a probabilistic programming language in TensorFlow for deep generative models and variational inference.