facebookincubator/muse-gadget-sdk

Open source SDK to build Muse gadgets

What it solves

Muse Gadgets provides the software infrastructure to turn off-the-shelf hardware, such as ESP32 microcontrollers and Raspberry Pi devices, into custom interactive gadgets that interface with the Muse AI ecosystem.

How it works

The project provides two primary SDKs: one for ESP32-based microcontrollers and one for Linux-based systems (like the Raspberry Pi). These SDKs allow you to connect hardware components—such as displays, sensors, and actuators—to the Muse app. Once configured with an SDK token, these devices pair with the Muse mobile application, allowing them to act as physical interfaces for AI agents and system tasks.

Who it’s for

This project is for hardware hackers, makers, and developers who want to build custom physical devices that integrate with AI agents or home automation systems.

Highlights

  • Supports ESP32 microcontrollers for low-power, embedded applications.
  • Supports Linux-based hardware for more complex tasks like system administration or Home Assistant integration.
  • Includes tools for power profiling and diagnostic testing of custom hardware.
  • Open-source firmware and SDKs designed for extensibility and DIY hardware projects.

Related

  • Dispatch
    Meta Muse Gadgets SDK: Open‑Source Hardware Integration for Muse AI

    Meta released the Muse Gadgets open‑source SDKs for ESP32 and Linux, letting developers build custom hardware that talks to the Muse AI agent.

  • Project
    Adolanium/hermes-gadget-sdk

    Hermes Gadget is an open-source SDK and firmware for building a physical, push-to-talk voice interface for an AI agent like Hermes. It runs on ESP32-S3 and Raspberry Pi boards, includes a desktop simulator, and lets the agent control the device's LEDs and sensors as tools.

  • Dispatch
    Meta Muse filesystem export reveals 6.8 GB of internal runtime files

    A Mouse researcher prompted Meta’s Muse agent to archive its visible filesystem, receiving a 6.8 GB zip that exposed internal docs, integration code, container scripts, memory stores, and experimental Home Link hardware guides, prompting a bug‑bounty report that Meta marked “Not Applicable.”

  • Project
    win4r/MuseAI-Skills

    MuseAI‑Skills is a snapshot of Muse AI’s skill definitions, configs, and runtime scripts – a reference for agent workflow design, not a full open‑source AI engine.

  • Dispatch
    Muse Spark 1.1 Release Notes

    Meta Superintelligence Labs has released Muse Spark 1.1, a multimodal reasoning model optimized for agentic tasks, coding, and computer use, now available via the new Meta Model API.