liyupi/ai-guide

程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cursor / Claude Code / TRAE / Codex / Copilot）、AI 开发框架教程（Spring AI / LangChain）、AI 产品变现指南，帮你快速掌握 AI 技术，走在时代前沿。本项目为开源文档 aiguide，已升级为鱼皮 AI 导航网站

What it solves

This project tackles the information gap around AI tools and techniques. Many people — especially beginners — have trouble finding reliable, up-to-date guidance on using AI products effectively. The repository gathers a wide range of AI-related resources into one free, openly accessible place, so anyone can learn practical AI skills without paying for expensive courses or scrolling through scattered sources.

How it works

The project is a structured knowledge base, mainly written in Chinese, that compiles:

  • AI tool introductions and usage guides – covering models like DeepSeek, GPT-5, Claude, Gemini, and tools like Cursor.
  • Hands-on tutorials – including a popular “Vibe Coding” zero-to-basics course that teaches people to build and launch their own AI-powered products.
  • Tool reviews and comparisons – offering practical evaluations of various AI products.
  • Application scenarios – like video creation, office productivity, knowledge management, and job hunting.
  • Monetization advice – how to turn AI products into income.
  • Industry news and resources – keeping readers informed.

Content is organised into folders by topic, and the README provides a quick navigation table with direct links to each section. The project also includes a companion video course and an online reading site. Contributions are encouraged, and the content is licensed under a non-commercial share-alike license.

Who it’s for

This is built for anyone curious about AI — from complete beginners with zero technical background to developers who already code. It’s especially useful for people who want to start using AI tools to build things, improve productivity, or create income streams. The project explicitly aims to help non-programmers (designers, product managers, creators) get started with AI as well.

Highlights

  • Completely free and open – all content is publicly accessible with no paywall.
  • Comprehensive Vibe Coding tutorial – a detailed, illustrated course covering basics, tooling, project practice, tips, monetisation, and advanced topics.
  • Structured navigation – tables and folder organisation make it easy to find specific resources quickly.
  • Active community and contributions – encourages readers to join, share, and help build the knowledge base.
  • Dual licensing – content uses CC BY-NC-SA 4.0 (non-commercial) while the website code is MIT licensed.

Related

  • Project
    awesome-dsh-plugin/awesome-dsh-plugin

    A curated, community-maintained directory of plugins for the DeepSeek Harness agent framework, enabling users to easily discover and install extensions to customize their coding agent's capabilities.

  • Project
    1jehuang/jcode

    jcode is a high-performance framework for running multiple AI coding agents in parallel, featuring native swarm collaboration, autonomous self-improvement, and significantly lower memory overhead than traditional coding assistants.

  • Project
    dyad-sh/dyad

    Dyad is a local, open-source AI app builder that allows users to create applications privately on their own machines using their own API keys.

  • Project
    walkinglabs/learn-harness-engineering

    Learn Harness Engineering is an open-source course teaching how to build the environment (harness) that makes AI coding agents reliable. It covers five subsystems (instructions, state, verification, scope, session lifecycle), includes 14 lectures, 8 projects, and a resource library of templates. You can start by adding four files (AGENTS.md, init.sh, feature_list.json, claude-progress.md) to your repo. The course is available in 15 languages and includes recent updates on frontier harness designs, graph engineering, and loop engineering.