YuFan Luo

Night-Journal. 晚记 Night Journal — 白天丢碎片，夜里成日记。Mobile-first AI diary that turns scattered fragments into coherent entries overnight. Self-hosted · Docker one-command deploy · PWA installable.

openscreen. Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

Recordly. Create polished demo videos without editing skills. Mac/Windows/Linux

taste-skill. Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

ctx. Search the coding agent history already on your machine

deepeval. The LLM Evaluation Framework

Webwright. A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

science-skills. GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.

claw-orchestrator. Run Claude Code, Codex, Gemini, Cursor Agent and custom coding CLIs as one unified runtime for claw-style agent systems. Runs standalone, with first-class OpenClaw plugin support.

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

harbor. Framework for evaluating and improving agents

zed. Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

native. Toolkit for building native desktop apps

starter. The starter kit for your mintlify project

mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

warp. Warp is an agentic development environment, born out of the terminal.

tokenshrink. Same AI, fewer tokens. Free forever. — tokenshrink.com

rtk. CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

rosclaw. ROS2 meets OpenClaw 💗

huashu-design. Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic

dianlipoikmo. 电力宝可梦

CLI-Anything. "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

system-prompts-and-models-of-ai-tools. FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

Sequential-thinking-skills. Sequential thinking for AI agents: a reusable skill and CLI runtime for stepwise reasoning, revision, replay, and convergence — no extra MCP server required.

context-hub. JavaScript

Nexus-skills. AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱，精准查询文件结构、依赖关系与改动影响半径。

FileToVox. Tool for convert files into Magicavoxel file

marketingskills. Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

Humanizer-zh. Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。

MemSkill. MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Tribes. Tribes is an open source implementation for AI research of the game The Battle of Polytopia

openscreen. Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

voyager. Voyager — an all-in-one enhancement suite for AI Studio, Gemini, Claude & ChatGPT: timelines, folders, prompts, usage tracking, chat export, plugins, and more. / 面向 AI Studio、Gemini、Claude 与 ChatGPT 的全能增强套件。

ANWS. 🚀 A spec-driven workflow framework for AI-assisted development. Empowers prompt engineers to build production-ready software through structured PRD → Architecture → Task decomposition. Designed for Antigravity to enforce design-first principles and prevent architectural drift in vibe coding.🗺️Antigravity-Workflow-System

word2md. Word to Markdown Converter(word2md.net),Free,Fast,Secure

AntigravityQuotaWatcher. Google Antigravity AI模型配额监控插件 (Antigravity AI Model Quota Watching)

CET6-Resources. 英语六级CET6资源

openskills. Universal skills loader for AI coding agents - npm i -g openskills

dustinwin.github.io. mihomo 和 sing-box 教程合集——安装、配置、自定义规则、DNS 分流

MineContext. MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

deeplearning.ai-andrewNG. deeplearning.ai , By Andrew Ng, All slide and notebook + data + solutions and video link

Deep-Learning-Coursera. Deep Learning Specialization by Andrew Ng, deeplearning.ai.

deeplearning_ai_books. deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

spec-kit. 💫 Toolkit to help you get started with Spec-Driven Development

PromptKey. 一个专为 AI 重度用户设计的系统级提示词管理器，支持全局快捷键、智能应用上下文感知和专业模板管理，让用户在任何软件中一键调用高质量 Prompt

ipex-llm. Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.

tldr. Collaborative cheatsheets for console commands 📚.

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

Claude-Code-Remote. Control Claude Code remotely via email、discord、telegram. Start tasks locally, receive notifications when Claude completes them, and send new commands by simply replying to emails.

happy-llm. 📚 从零开始构建大模型

DictionaryData. 高质量英语字典，400多本单词书+60000多个单词！单词书包括小学、中学、高中、考研、考博、出国（GRE、托福等等）等等，难道它不香吗？

kimi-cc. Use Kimi latest model(kimi-k2-0711-preview) to drive your Claude Code.

MediaCrawler. 小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

PDFMathTranslate. [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

opcode. A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

awesome-machine-learning. A curated list of awesome Machine Learning frameworks, libraries and software.

pokemon-dataset-zh. 宝可梦（1~9世代）简体中文JSON数据集 | Simplified Chinese Pokémon (Gen 1-9) dataset in JSON format

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

penpot. Penpot: The open-source design platform for Product teams that need scalable collaboration.

onlook. The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI

camel. 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

UI-TARS. Pioneering Automated GUI Interaction with Native Agents

docling. Get your documents ready for gen AI

h2o-wizardlm. Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning

WeChatMsg.

LightRAG. [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

halo. Halo 是一款强大易用的开源建站工具，从个人博客、知识库，到企业官网、在线商城，Halo 都能助您轻松实现，一站式满足您的多样化建站需求。

cs-self-learning. 计算机自学指南

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Tianji. 制作懂人情世故的大语言模型 | 涵盖提示词工程、RAG、Agent、LLM微调教程

UCBerkeley-CS61A-Fall2023. This repo contains all the materials and solutions of UC Berkeley CS 61A fall semester 2023

AI-Guide-and-Demos-zh_CN. 这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。

ControlNet. Let us control diffusion models!

wenda. 闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.