Content
# Layer Prompt Manager

Save, version, and manage custom AI prompts for your code repositories. Seamlessly integrate with AI-powered IDEs like Cursor and GitHub Copilot.
## Features
### 1. Save Prompts from Your IDE
Create and save custom prompts directly from your AI-powered IDE. The MCP server connects your development environment to Layer, allowing you to build a library of effective prompts specific to your codebase.
### 2. Version Control for Prompts
Track the evolution of your prompts over time. Compare different versions to see which ones produce the best results. Easily roll back to previous versions when needed.
### 3. Layer Prompts
- Access all your Layer prompts
- Edit existing prompts
- Create new prompts for AI-powered coding assistants
- Manage prompt versions
### 4. Templates
- Use pre-existing templates
- Create your own templates
- Standardize AI interactions across your development team
- Share and reuse common prompt patterns
### 5. Modern UI
- Matrix-inspired design
- Dark mode interface
- Responsive layout
- Interactive components
## Project Structure
```
├── frontend/
│ ├── app/
│ │ ├── prompts/ # Prompt management pages
│ │ ├── templates/ # Template management pages
│ │ ├── tools/ # Tool-related components
│ │ └── docs/ # Documentation pages
│ ├── components/ # Reusable UI components
│ └── lib/ # API and utility functions
├── backend/
│ └── main.py # FastAPI backend server
```
## Setup Instructions
### Prerequisites
- Node.js (v16 or higher)
- Python 3.8+
- pip
- SQLite
### Backend Setup
1. Create a virtual environment:
```bash
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Create a `.env` file in the root directory:
```env
LAYER_API_KEY=your_layer_api_key
LAYER_BASE_URL=https://api.buildwithlayer.com
```
4. Start the backend server:
```bash
uvicorn main:app --reload
```
### Frontend Setup
1. Install dependencies:
```bash
cd frontend
npm install
```
2. Create a `.env.local` file:
```env
NEXT_PUBLIC_API_URL=http://localhost:8000
```
3. Start the development server:
```bash
npm run dev
```
## Usage
1. **Creating Prompts**
- Navigate to "Layer Prompts"
- Click "Create New Prompt"
- Fill in prompt details, steps, and arguments
- Save and version your prompt
2. **Managing Templates**
- Go to "Templates"
- Create new templates or use existing ones
- Edit and customize templates for your team
3. **Version Control**
- Each prompt can have multiple versions
- Add change notes for version tracking
- Compare and restore previous versions
## Environment Variables
Backend (`.env`):
```env
LAYER_API_KEY=your_layer_api_key
LAYER_BASE_URL=https://api.buildwithlayer.com
```
Frontend (`.env.local`):
```env
NEXT_PUBLIC_API_URL=http://localhost:8000
```
## .gitignore
```gitignore
# Dependencies
node_modules/
venv/
__pycache__/
# Environment variables
.env
.env.local
.env.development.local
.env.test.local
.env.production.local
# Build outputs
.next/
build/
dist/
# IDE
.vscode/
.idea/
# Database
*.db
*.sqlite3
# Logs
*.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
# System Files
.DS_Store
Thumbs.db
```
## Contributing
1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request
## License
MIT License - feel free to use this project for your own purposes.
Connection Info
You Might Also Like
markitdown
MarkItDown-MCP is a lightweight server for converting URIs to Markdown.
servers
Model Context Protocol Servers
Time
A Model Context Protocol server for time and timezone conversions.
Filesystem
Node.js MCP Server for filesystem operations with dynamic access control.
Sequential Thinking
A structured MCP server for dynamic problem-solving and reflective thinking.
git
A Model Context Protocol server for Git automation and interaction.