Msg-Use

AI-powered message scheduler using browser agents and Gemini. Schedule personalized messages in natural language and let AI compose them intelligently.

[!CAUTION] This demo requires browser-use v0.7.7+.

Features

Agent logs into WhatsApp Web automatically
Parses natural language scheduling instructions
Composes personalized messages using AI
Schedules messages for future delivery or sends immediately
Persistent session (no repeated QR scanning)

Setup

Make sure the newest version of browser-use is installed:

pip install -U browser-use

Export your Gemini API key, get it from: Google AI Studio

export GEMINI_API_KEY='your-gemini-api-key-here'

First-time setup requires QR code scanning:

python whatsapp_login.py

Scan QR code when browser opens
Session will be saved for future use

Normal Usage

Edit your schedule in schedule.txt:

- Send "Hi" to Magnus on the 13.06 at 18:15
- Tell hinge date (Camila) at 20:00 that I miss her
- Send happy birthday message to sister on the 15.06
- Remind mom to pick up the car next tuesday

Test mode - See what will be sent:

python whatsapp_scheduler.py --test

Run scheduler:

python whatsapp_scheduler.py

Programmatic Usage

import asyncio
from whatsapp_scheduler import schedule_messages

async def main():
    messages = [
        "Send hello to John at 15:30",
        "Remind Sarah about meeting tomorrow at 9am"
    ]
    await schedule_messages(messages, debug=False)

asyncio.run(main())

Output

Example scheduling output:

[
  {
    "contact": "Magnus",
    "original_message": "Hi",
    "composed_message": "Hi",
    "scheduled_time": "2025-06-13 18:15"
  },
  {
    "contact": "Camila",
    "original_message": "I miss her",
    "composed_message": "I miss you ❤️",
    "scheduled_time": "2025-06-14 20:00"
  }
]

Files

whatsapp_scheduler.py - Main scheduler script
whatsapp_login.py - One-time login setup
schedule.txt - Your message schedule in natural language

License

MIT

README.md