# 📄 PAPER-CODE **The AI-Native Documentation Generator** [](https://www.python.org/) [](https://pypi.org/project/paper-code/) [](LICENSE) [](https://github.com/psf/black) [](docs/CONTRIBUTING.md) > **Stop writing boilerplate docs.** > Automatically generate **AI Context**, **Architecture Guides**, and **Governance Files** optimized for Cursor, Windsurf, and Copilot. [✨ Features](#-features) • [🚀 Installation](#-installation) • [📖 Usage](#-usage) • [🗺️ Roadmap](ROADMAP.md)

---

🎬 Demo

 _Watch PAPER-CODE generate AI-ready documentation in seconds_

---

🧐 Why PAPER-CODE?

In the era of AI coding, Context is King. If you ask an AI to “build a feature” without context, it generates generic, legacy code.

PAPER-CODE solves this by bootstrapping a robust documentation structure that serves two masters:

1. For AI Agents: Generates .cursorrules, AI_RULES.md, and strict coding standards to keep your AI (Cursor/Copilot) from hallucinating or using deprecated syntax.
2. For Humans: Creates professional ARCHITECTURE.md, CONTRIBUTING.md, and tech stack guides so your team stays on the same page.

✨ Features

• 🤖 AI-First Context: Auto-generates .cursorrules and prompt instructions tailored to your specific stack (e.g., “Use Next.js App Router, not Pages”).
• 🎯 Multi-Stack Support: Specialized templates for Frontend, Backend, Mobile, Game Dev, and ML.
• 📚 Library Awareness: Smart docs for 30+ libraries (Tailwind, Prisma, Redux, Zod…).
• 🛡️ Governance Ready: Generates LICENSE, CHANGELOG.md, SECURITY.md, and GitHub Issue Templates.
• 💻 Interactive & Batch: Use the beautiful CLI wizard or a JSON config file for automation.

🚀 Installation

Requires Python 3.10+.

1. Via PyPI (Recommended)

You can install PAPER-CODE directly from PyPI:

pip install paper-code

Upgrade (From PyPI)

To upgrade an existing system-wide or virtualenv installation of paper-code from PyPI to the latest released version:

# Upgrade to the latest version
pip install --upgrade paper-code

# Or to install a specific version (e.g., 0.1.0)
pip install paper-code==0.1.0

2. From Source (For Development)

If you want to contribute or use the latest development version:

# Clone the repository
git clone https://github.com/minhgiau998/paper-code.git
cd paper-code

# Install as an editable tool
pip install -e .

📖 Usage

1. Interactive Mode (Recommended)

Just run the command and follow the wizard.

paper-code

Terminal Output Preview:

🚀 Initializing documentation for: My Awesome Project
[?] Select Project Type: Frontend
[?] Select Frontend Stack: Next.js
[?] Select Modules/Libraries: [x] TailwindCSS, [x] Prisma, [x] NextAuth.js, [x] Zod

✨ Done! Generated AI-ready docs in ./docs

2. Quick Start (Templates)

Skip the questions if you know what you want.

paper-code --template "Next.js" --output ./my-app
paper-code --template "FastAPI" --output ./my-api

3. Batch Mode (For CI/CD)

Generate docs based on a configuration file.

paper-code --config paper.config.json --batch

🧩 Supported Stacks

PAPER-CODE isn’t just generic markdown. It contains deep, opinionated knowledge for:

Category	Supported Stacks
Frontend	React, Vue, Next.js, Nuxt.js, Angular, SvelteKit
Backend	Node.js (Express/NestJS/Fastify), FastAPI, Django, Go (Gin)
Mobile	React Native (Expo/CLI), Flutter
Desktop	Electron, Tauri v2
Data & ML	PyTorch, TensorFlow, Scikit-learn
Game Dev	Godot 4, Unity
CLI	Node.js (Commander), Python (Click), Go (Cobra), Rust (Clap)
Libraries	TypeScript Lib, Python Lib, Go Lib, Rust Lib

📂 Generated Structure

A typical Next.js + Prisma project generated by PAPER-CODE:

my-project/
├── .cursorrules             # 👈 Critical for AI Editors
├── .github/
│   ├── copilot-instructions.md
│   └── workflows/ci.yml
├── docs/
│   ├── ai/
│   │   ├── AI_RULES.md      # The "Constitution" for your AI
│   │   ├── AI_WORKFLOWS.md  # SOPs for common tasks
│   │   └── AI_CONTEXT.md    # Project map
│   ├── libs/                # Specific guides for libraries
│   │   ├── prisma.md
│   │   └── tailwindcss.md
│   ├── ARCHITECTURE.md
│   ├── CODE_STANDARDS.md    # "Do's and Don'ts"
│   ├── CONTRIBUTING.md
│   └── TESTING.md
├── CHANGELOG.md
└── README.md

🤝 Contributing

We love contributions! Whether it’s adding a new Tech Stack template or fixing a typo. Please read our CONTRIBUTING.md to get started.

1. Fork the repo.
2. Create your feature branch (git checkout -b feature/amazing-stack).
3. Commit your changes (git commit -m 'feat: add Astro support').
4. Push to the branch.
5. Open a Pull Request.

📄 License

Distributed under the MIT License. See LICENSE for more information.

Built with ❤️ by Developers, for Developers (and their AI assistants).