What is FastApps?
FastApps is a zero-boilerplate framework for building ChatGPT apps powered by OpenAI’s Apps SDK and FastMCP.
Quick Start
Get your first widget running in 5 minutes!
Why FastApps?
Building with the raw Apps SDK requires extensive boilerplate - protocol handlers, tool registration, resource management, and build configuration. FastApps eliminates all of that.
Quick Example
MCP Tool (Backend)
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!"
async def execute(self, input_data: MyWidgetInput) -> Dict[str, Any]:
return {"message": f"Hello, {input_data.name}!"}
React Widget (Frontend)
import React from 'react';
import { useWidgetProps } from 'fastapps';
export default function MyWidget() {
const props = useWidgetProps();
return <h1>{props.message}</h1>;
}
That’s all you need! FastApps handles everything else automatically.
Core Features
What You’ll Build
With FastApps, you can create:
- Interactive dashboards with real-time data
- Form widgets with validation and submission
- Data visualizations with charts and graphs
- API integrations that connect to external services
- Authenticated widgets with user-specific data
Ready to Get Started?
“You should write your widget logic and UI, not MCP boilerplate.”
Need help? Join our Discord community or check out the GitHub repository.
.png)


