Starlette

Minimal async Python API with Starlette.

PythonAPI

Get the AI prompt

What you can build with it

Tiny async services
Webhook endpoints
Streaming or long-poll APIs

What's inside

Starlette app
Example routes

Before you deploy

Make sure your app reads the PORT environment variable. The platform sets PORT=8080.

Source

github.com/vercel/vercel/tree/main/examples/starlette

Start with your AI

Paste this into Claude Code, Cursor, Codex or another AI coding assistant. It copies the template into your own private repo, deploys it to Elula and gives you the live URL.

Start a new project from the Starlette template at https://github.com/vercel/vercel/tree/main/examples/starlette and deploy it to Elula: copy the folder into a new private GitHub repo, install the Elula CLI if needed, then run elula init and elula deploy --no-wait. A deploy takes a few minutes: run elula status --wait 60 until it says Live, and tell me which step it's on each time. Run elula docs if anything is unclear. Give me the live URL.

View on GitHub

Deploy on Elula

Prefer the terminal? Start your own private copy and ship it with the CLI.

npx degit vercel/vercel/examples/starlette#main my-starlette
cd my-starlette && git init && git add -A && git commit -m "Start from the Starlette template"
gh repo create my-starlette --private --source . --push
elula init
elula deploy

Deploy from the dashboard Install the CLI

Clone the repo

Grab just this template's folder and run it locally.

git clone --depth 1 --filter=blob:none --sparse -b main https://github.com/vercel/vercel.git
cd vercel && git sparse-checkout set examples/starlette
cd examples/starlette