Pocket Agent

A voice-enabled AI agent built for the Waveshare ESP32-S3 1.75" AMOLED round display.

Repository Structure

pocket_agent/
├── smart-agent/   # Main project code (Python app + ESP32 firmware)
└── esp-idf/       # ESP-IDF v5.2.1 (git submodule)

Cloning

Clone with submodules to include ESP-IDF:

git clone --recurse-submodules https://github.com/rickenator/pocket_agent.git

If you already cloned without --recurse-submodules, run:

git submodule update --init

Getting Started

All project documentation lives in smart-agent/.

• Quick Start — Get running in 5 minutes
• Architecture — System design and component overview
• Project Summary — Feature and module reference
• ESP32 Setup — Firmware build and flash guide
• AI Client — STT / Ollama / TTS pipeline details
• WiFi Provisioning — Network setup details
• TODO — Project roadmap and planned features
• Contributing — How to contribute to this project

License

MIT License — see smart-agent/README.md for details.