FreeLLMDIY AI Tamagotchi built on Meta’s Muse Charm hardware for $50
A creator modified a $50 Waveshare ESP32‑S3 pendant to run Meta’s Muse AI, adding voice, avatars and a remote camera viewfinder.
Sean Hollister bought a 1.75‑inch touchscreen pendant from Waveshare for $50 and used it as a Muse Charm‑style AI gadget.
The device, an ESP32‑S3 board, is officially supported by Meta as a “Muse Gadget” that connects to the Muse AI cloud using open‑source code and tokens.
Initial setup paired the pendant with the Muse phone app, but the AI only displayed short text and responded slowly, lacking voice output and smart‑home discovery.
Hollister used Claude to rewrite the firmware, adding a conversation history view, a British ElevenLabs voice for spoken replies, and a Bluetooth‑enabled remote camera preview.
The updated gadget can trigger the phone’s camera, stream a low‑quality preview, and display custom avatars and a Tamagotchi‑style minigame.
What it means for you
The hack shows that inexpensive ESP32 hardware can run Meta’s Muse AI with community‑built software, giving hobbyists a low‑cost entry to voice‑enabled AI assistants. It also highlights how open‑source tools like Claude can extend the functionality of proprietary AI platforms for personal projects.
Sources
- I built an AI Tamagotchi before Meta could, The Verge, 31 Oct 2026
- muse-gadget-sdk/android/musegadgetstest at main · facebookincubator/muse-gadget-sdk · GitHub, github.com (official), 31 Oct 2026
Written automatically from the sources above, then checked by our code: every number and name must appear in them, and no sentence may copy a source. Spotted a mistake? Report it.
Which AI can you use for free today?
Every free AI model, ranked by blind human votes, with the memory and speed it needs on your own GPU.