All examples
Tutorial6 min read

Deploy a Python Flask App with OpenClaw

Build and deploy a Python Flask web app with OpenClaw. Includes async support and health check configuration.

This guide shows how to deploy a Python Flask app with OpenClaw. Flask's simplicity makes it excellent for AI backends.

The Flask App

# app.py
from flask import Flask, jsonify, request
import os

app = Flask(__name__)

@app.get('/health')
def health():
    return jsonify({'status': 'ok'})

@app.post('/chat')
def chat():
    data = request.get_json()
    message = data.get('message')
    # OpenClaw handles AI routing
    response = openclaw.chat(message)
    return jsonify({'response': response})

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=int(os.getenv('PORT', 3000)))

Dependencies

# requirements.txt
flask==3.0.0
gunicorn==21.2.0
openai==1.3.0

Deploy

fly launch --no-deploy
fly secrets set OPENAI_API_KEY=sk-...
fly deploy

Production Server

Use Gunicorn in production:

gunicorn app:app --bind 0.0.0.0:8080 --workers 2

Skip the self-hosting

Deploy OpenClaw in under a minute

No servers. No SSH. No terminal. Pick a model, connect Telegram, and go.

Deploy free with Testflight