# Vibe Coding Stack: A Personal AI-Driven Development Workflow Control Plane

> A versionable personal AI development control plane that integrates skills, prompts, MCP tools, knowledge hubs, and workflows. It supports automatic generation of plans and outputs from conversation records, creating an evolvable AI-assisted development environment.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-05-24T18:15:22.000Z
- 最近活动: 2026-05-24T18:26:24.120Z
- 热度: 163.8
- 关键词: Vibe Coding, AI辅助开发, Cursor, 提示词工程, 知识管理, MCP协议, 工作流, 个人知识库, AI代理, 开发效率
- 页面链接: https://www.zingnex.cn/en/forum/thread/vibe-coding-stack-ai
- Canonical: https://www.zingnex.cn/forum/thread/vibe-coding-stack-ai
- Markdown 来源: floors_fallback

---

## Introduction / Main Floor: Vibe Coding Stack: A Personal AI-Driven Development Workflow Control Plane

A versionable personal AI development control plane that integrates skills, prompts, MCP tools, knowledge hubs, and workflows. It supports automatic generation of plans and outputs from conversation records, creating an evolvable AI-assisted development environment.

## Original Author and Source

- **Original Author/Maintainer**: spacebuilder13
- **Source Platform**: GitHub
- **Original Title**: vibe-coding-stack
- **Original Link**: https://github.com/spacebuilder13/vibe-coding-stack
- **Publication Date**: May 24, 2026

---

## Background: Organizational Challenges in AI-Assisted Development

With the popularity of AI coding assistants like Cursor, Claude, and GitHub Copilot, 'Vibe Coding' has become a hot concept in the developer community. This development model emphasizes smooth collaboration with AI, allowing developers to focus on high-level intentions while delegating implementation details to AI. However, as the AI toolchain expands, a new problem emerges: How to effectively organize these tools? How to make AI understand your tech stack and preferences in every conversation? How to avoid repeating context explanations in each round of dialogue?

The Vibe Coding Stack project by spacebuilder13 is designed to address these organizational issues. It provides a **personalized, versionable control plane** for managing all elements of AI-assisted development.

---

## Project Overview

Vibe Coding Stack is a structured knowledge base and configuration collection, not a fixed template. Its core idea is: Your AI development environment should be an **evolvable source of truth** that continuously updates as you discover better patterns, rather than a disposable scaffold.

Main uses of the project include:

**For each development session**: Clone or submodule this repository, let Cursor/Claude read `AGENTS.md` and `.cursor/rules`, and automatically inherit default configurations.

**For continuous evolution**: Bump the `VERSION`, append to `CHANGELOG.md`, add new knowledge hubs and prompts, and record the best practices you've discovered.

**Ultimate goal**: Ingest a **recorded conversation** (or transcribed text) about someone's problem; the AI can produce a **plan plus the first concrete output** before the conversation ends—without you having to manually repeat context explanations.

---

## Repository Structure Analysis

The project uses a clear layered structure, with each directory having a distinct responsibility:

## Configuration Layer

| Path | Role |
|------|------|
| `AGENTS.md` | Agent Entry: Priority, tech stack hierarchy, when to use what |
| `.cursor/rules/vibe-stack.mdc` | Cursor native rule file: Reinforces the same configuration |

These two files form the 'onboarding materials' for AI assistants. When the AI starts working, it first reads these files to understand the project's tech stack, priorities, and working methods.

## Architecture Layer

| Path | Role |
|------|------|
| `boards/` | Architecture Board: Single source of truth, including ingestion v3 diagrams, blueprints, and local previews |
| `docs/github-landscape.md` | Your public GitHub work evolution date snapshot (context, not a rule) |
| `docs/mde-agent-flow.md` | Consumable architecture writing example (Markdown + Mermaid + conventions) |

This layer focuses on the documentation and visualization of system design. The architecture board provides a high-level view, the GitHub landscape records historical evolution, and the architecture document demonstrates how to write technical documents in a consumable way.

---

## Knowledge Layer

| Path | Role |
|------|------|
| `hubs/` | Knowledge Hubs: Checklists and conventions for Notebook LM, documents, design sources, Magic Patterns links, etc. |
| `notebooks/` | Runnable narrative demos (`Markdown -> Code -> Visualization`) for explainable workflows |
| `prompts/` | Reusable prompt shells (handover, plan prioritization, release cycle) |

The knowledge layer is the core asset of the project. Knowledge hubs are structured information repositories, notebooks combine documents with executable code, and prompts are validated interaction templates.