Skip to main content

Control a coding agent from WhatsApp

Project description

what_code

A coding agent you control from WhatsApp. Send a text or voice message, and it writes code directly on your machine.

Built with MiniMax-M2.7, Groq Whisper, and Twilio.

Install

pip install what-code

Setup (~5 minutes)

Run the interactive setup wizard:

what_code setup

It walks you through creating 3 free accounts and entering your API keys:

Service What it does Sign up
MiniMax Powers the AI agent + voice replies platform.minimaxi.com
Groq Transcribes your voice notes console.groq.com
Twilio Sends/receives WhatsApp messages twilio.com/try-twilio

All three have free tiers. No credit card required.

Start

what_code start

The CLI will guide you through:

  1. Webhook URL -- copy it into your Twilio Sandbox settings
  2. QR code -- scan it to connect your WhatsApp
  3. Start coding -- send a message and the agent builds it

What can it do?

Send messages like:

  • "create a flask API with user authentication"
  • "read the files in my project folder"
  • "fix the bug in app.py"
  • Or send a voice note -- it understands speech too

The agent has full access to your filesystem. It can read, write, and run commands on your machine.

WhatsApp Commands

Command Action
\help List commands
\clear Reset conversation
\pwd Show working directory
\cd <path> Change directory
\ls List files
\history Conversation summary

How it works

You (WhatsApp) --> Twilio --> ngrok --> FastAPI server --> MiniMax-M2.7
                                                              |
                                                         Tool calls:
                                                         - read_file
                                                         - write_file
                                                         - run_command
                                                         - list_directory
                                                         - make_directory

Voice notes are transcribed with Groq Whisper, and voice replies use MiniMax TTS.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

what_code-0.1.1.tar.gz (11.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

what_code-0.1.1-py3-none-any.whl (12.1 kB view details)

Uploaded Python 3

File details

Details for the file what_code-0.1.1.tar.gz.

File metadata

  • Download URL: what_code-0.1.1.tar.gz
  • Upload date:
  • Size: 11.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.7

File hashes

Hashes for what_code-0.1.1.tar.gz
Algorithm Hash digest
SHA256 2e6a06c5f6c7cdcb847e08064684e056c7e9e7342ef77f5e445d5664ec3db38c
MD5 5511d327f75fc0050ee0d66cd0040f6f
BLAKE2b-256 864867c56dbbe34a4d708b6deb7631e36510f99d18672dc8a91baaeb4cefc083

See more details on using hashes here.

File details

Details for the file what_code-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: what_code-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 12.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.7

File hashes

Hashes for what_code-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ea4013a2b5dd85a9e80f34c2a4d63ea764e3a9d7c2c414adece3a570dd99598c
MD5 648f066d01c88af6efccfd6c66666afc
BLAKE2b-256 e154e221d353f10023a12b1bbd282fdebaf7e75f5691640ae97ce8d20bdb3c1c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page