The python framework for apps in ChatGPT

📚 Documentation: https://docs.fastapps.org/

👥 Community: Join Our Discord

We recommend installing FastApps with uv:

uv tool install fastapps
uv tool install --upgrade fastapps # Update to the latest version

For full installation instructions, including verification, upgrading from the official MCPSDK, and developer setup, see the Installation Guide.

then, you can quickstart by running commands below :

fastapps init my-app
cd my-app
fastapps dev

That's it! You'll gonna see an image with a public url. You can test the server with following guides.

The public url is one-time, generated with cloudflare tunnel.

MCP server is available at /mcp endpoint of fastapps server.
Example : https://your-public-url.trycloudflare.com/mcp

Option A: Test on MCPJam Inspector

Add your public URL + /mcp to ChatGPT.

npx @mcpjam/inspector@latest

Option B: Test on ChatGPT

Add your public URL + /mcp to ChatGPT's "Settings > Connectors" .

fastapps create additional-widget

FastApps provides pre-built templates to jumpstart your widget development:

# Create widget from a template
fastapps create my-list --list          # Vertical list with items
fastapps create my-carousel --carousel  # Horizontal scrolling cards
fastapps create my-albums --albums      # Photo gallery viewer

You'll only need to edit these 2 folders:

This folder contains backend .py files, where you define conditions & server logics for the app.

Example :

### my_widget_tool.py
from fastapps import BaseWidget, Field, ConfigDict
from pydantic import BaseModel
from typing import Dict, Any

class MyWidgetInput(BaseModel):
    model_config = ConfigDict(populate_by_name=True)
    name: str = Field(default="World")

class MyWidgetTool(BaseWidget):
    identifier = "my-widget"
    title = "My Widget"
    input_schema = MyWidgetInput
    invoking = "Processing..."
    invoked = "Done!"
    
    widget_csp = {
        "connect_domains": [],      # APIs you'll call
        "resource_domains": []      # Images/fonts you'll use
    }
    
    async def execute(self, input_data: MyWidgetInput) -> Dict[str, Any]:
        # Your logic here
        return {
            "name": input_data.name,
            "message": f"Hello, {input_data.name}!"
        }

The folder contains frontend component codes that will show up on the app screen according to the rules you've define with python codes above.

Apps in GPT components are react components - FastApps follows it. You can custom compoenents as you wish.

// my-widget/index.jsx
import React from 'react';
import { useWidgetProps } from 'fastapps';

export default function MyWidget() {
  const props = useWidgetProps();
  
  return (
    <div style={{
      padding: '40px',
      textAlign: 'center',
      background: '#4A90E2',
      color: 'white',
      borderRadius: '12px'
    }}>
      <h1>{props.message}</h1>
      <p>Welcome, {props.name}!</p>
    </div>
  );
}

That's it! These are the only files you need to write.

We welcome contributions! Please see our contributing guidelines:

• Contributing Guide - How to contribute to FastApps
• Code Style Guide - Code formatting and style standards
• GitHub Workflows - CI/CD documentation

# Fork and clone the repository
git clone https://github.com/YOUR_USERNAME/FastApps.git
cd FastApps

# Install uv (if not already installed)
# curl -LsSf https://astral.sh/uv/install.sh | sh

# Install development dependencies (recommended - matches CI)
uv sync --dev

# Or use pip (traditional approach)
# pip install -e ".[dev]"

# Install pre-commit hooks (already installed via uv sync --dev)
pre-commit install

# Make changes and ensure they pass checks
black .
ruff check --fix .
pytest

# Submit a pull request

MIT © Dooi Labs

• PyPI: https://pypi.org/project/fastapps/
• React Hooks: https://www.npmjs.com/package/fastapps
• GitHub: https://github.com/DooiLabs/FastApps
• MCP Spec: https://modelcontextprotocol.io/