Observed arrival · 2026-10-15
FUMI, an AI companion with a physical body
FUMI is an open-source ESP32-S3 project that combines a touch-screen character, simple life systems, and voice interaction with cloud AI.
- For
- ESP32-S3 makers exploring embodied AI companions
- Worth noticing
- Alternative ESP32-S3 boards are not plug-and-play; display and audio drivers need adapting.
Field notes
The current reference build targets the Waveshare ESP32-S3 Touch LCD 1.46″; alternative boards require display and audio driver adaptation, and the page labels them hardware paths rather than plug-and-play firmware targets. Its voice sequence sends microphone audio through speech recognition and a selected model, then returns synthesized speech to the speaker; listed backend options include OpenAI, Claude, Grok, OpenRouter, and Ollama-compatible APIs.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue