Trending Projects

A TypeScript-based platform that aggregates various LLM APIs into a single hub for easy access and integration.

Estimates dense, flicker-free, geometrically consistent depth from monocular video for computer vision applications.

Unofficial Parallel WaveGAN repository with PyTorch implementation of various neural vocoders for speech synthesis.

A Python library that provides a wrapper for the ComfyUI AI model integration framework.

A series of code large language models developed by PKU-KCL for AI-powered coding and developer tooling.

Hyperparameter optimization library for TensorFlow and Keras, focused on AI/ML model development.

DLRover is an automatic distributed deep learning system for training large-scale AI models on Kubernetes.

ModernBERT brings the BERT language model into the modern era with architecture changes and scaling.

GLM-5 LLM framework enabling agentic AI development and autonomous coding workflows

A comprehensive collection of data augmentation resources and techniques for developers working with AI tools.

A fast 3D mesh reconstruction library with UV-unwrapping and illumination disentanglement for vibe coders.

The Pile is a large, diverse language model training dataset for use in AI research and development.

This GitHub repository provides a collection of tools for controllable video and image generation, including AI-powered animation and ControlNeXt.

Grad-CAM is a deep learning visualization technique for interpreting and explaining CNN-based models.

A Python library that makes it easy to deploy LangChain apps using Jina and FastAPI in production.

A collection of Python code and resources related to natural language processing tasks like topic modeling, text classification, and machine translation.

LocalAGI is a self-hostable AI agent platform focused on privacy and flexibility, with advanced capabilities for consumer-grade hardware.

A model-agnostic framework for extracting features from machine learning models at any resolution.

DATAGEN is an AI-driven multi-agent research assistant that automates hypothesis generation, data analysis, and report writing.

Reference implementations of several LangChain agents as Streamlit apps for AI-powered developers.

A roadmap to become a Visual SLAM (Simultaneous Localization and Mapping) developer in 2023.

An open-source e-book on building applications with large language models (LLMs), including prompt engineering, architecture design, and more.

A next-generation text translation tool that uses AI capabilities to instantly translate novels, games, and subtitles.

Rinha de Backend is a Lua-based backend framework and development platform for building AI-powered applications.

A comprehensive survey of deep learning techniques for 3D point cloud analysis, covering classification, detection, segmentation, and tracking.

A collection of GAN implementations in PyTorch, including progressive growing of GANs.

Build, enrich, and transform datasets using AI models with no code

A collection of modular datasets generated by GPT-4 for AI code generation and prompt engineering.

Semantic search and document parsing tools for the command line, built with Rust.

An intelligent trading bot that generates signals and trades using machine learning and feature engineering.

A PyTorch library for obtaining higher-order gradients over complex training loops.

A guide to learn about Transformer models, a foundational architecture for natural language processing.

Open-source codebase for a paper on using evolution strategies for scalable reinforcement learning.

This repository contains a collection of machine learning interview questions for developers to prepare for interviews.

A curated list of resources for developing applications using large language models (LLMs) with the Retrieval Augmented Generation (RAG) pattern.

Swift API for MLX, a platform focused on enabling developers to build with AI tools.

A curated list of papers and resources on text style transfer, a task in natural language processing.

A Python library for creating AI-generated artwork using Stable Diffusion models.

A diffusion-based model for generating realistic talking portrait videos.

A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

An official paper from CVPR 2024 on a talking head synthesis model that focuses on audio-driven synchronization.

Inference tool for Microsoft's Florence2 Versatile Language Model (VLM), built for vibe coders using AI tools.

A curated list of Tiny Object Detection papers and related resources for developers working with AI-powered computer vision.

A deep learning gateway for Raspberry Pi and other edge devices, enabling AI inference at the edge.

This open-source project provides clarity on the current state of the fast-paced open-source AI landscape.

A fast and scalable SVM library for classification and regression tasks on GPUs and CPUs.

Bailing is an open-source AI voice assistant built with ASR, LLM, and TTS, supporting low-latency response on low-end devices.

A Python library that provides building blocks for rapid development of generative AI applications.

SmoothQuant is an efficient post-training quantization tool for large language models, enabling accurate and fast inference.

verl-agent is a Python framework for training LLM/VLM agents using reinforcement learning.