AI 开源项目榜。

AOS Community Edition: the open agent operating system.

Open GenAI Stack

谷歌新书Agent设计模式(agentic design patterns)最佳中文版，持续优化。附：在线阅读、pdf和epub电子书下载。

Cross-session memory. Reads local memory state and injects it into the system prompt through hooks. Part of Unicity AOS.

Filesystem tools for agents. Read, write, replace, grep, list, create, delete, move via VFS airlock. Part of Unicity AOS.

Notebooks and code for the book "Introduction to Machine Learning with Python"

The first GitHub Copilot, Codeium and ChatGPT Xcode Source Editor Extension

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabilities.

Building a quick conversation-based search demo with Lepton AI.

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

Simple feed-forward neural network in JavaScript

Build autonomous AI agents in Python.

我的 ComfyUI 工作流合集 | My ComfyUI workflows collection

Find duplicate files

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

A simple task management system for managing AI dev agents

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

OpenAI + LINE + Vercel = GPT AI Assistant

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

AI powered Kubernetes Assistant

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Using Low-rank adaptation to quickly fine-tune diffusion models.

Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Tools for merging pretrained large language models.

Large World Model -- Modeling Text and Video with Millions Context