Meta Open Sources Code for DIY Muse AI Hardware Gadgets
Meta has open-sourced the code for its Muse AI agent, allowing developers to build custom hardware gadgets using Raspberry Pi, ESP32 boards, and other off-the-shelf components.
Meta has officially made the source code for its new Muse AI agent open source, enabling developers and hardware hobbyists to construct their own custom "Muse gadgets." This release transitions the AI assistant from a purely digital presence into the physical world, allowing individuals to design and program dedicated hardware interfaces that run the agent.
By providing the necessary software development kits (SDKs) and code, Meta is encouraging a hands-on, do-it-yourself approach to AI hardware. The initiative allows creators to build physical touchpoints for the Muse agent using accessible, off-the-shelf components.
Building Custom Muse Hardware
The open-source code supports a variety of hardware configurations, giving developers the flexibility to choose their physical medium. Meta has suggested several practical use cases for these DIY devices. For instance, developers can deploy Muse onto a color E Ink display to act as a dedicated home reminder board. Alternatively, the software can be loaded onto an HDMI stick, allowing users to project and interact with the Muse AI agent on a television or large monitor. Another suggested concept is installing Muse on a compact touchscreen device, creating a physical object that resembles a DIY "Muse Charm."
To facilitate these builds, Meta is targeting widely available hobbyist hardware platforms. According to the company, "Muse gadgets are open source devices you build yourself." Builders can "Program an off-the-shelf ESP32 board or set up a Raspberry Pi with our SDKs, then connect Muse to your displays, buttons, sensors, actuators, and whatever else you’ve got lying on your workbench." Despite providing these tools, Meta has also issued a lighthearted warning to those diving into the hardware assembly, advising developers to "Proceed at your own risk!"
The Muse Home Link Giveaway
Alongside the open-source code release, Meta is distributing a pre-built physical device called the Muse Home Link. This gadget serves as a reference design and a practical tool for smart home integration. By leveraging community-developed skills, users can command the Muse Home Link to interact with various household appliances and office equipment. According to Meta, the device can be used to "turn on a light, control your TV, send a document to a printer, and more, depending on your setup."
According to Nat Friedman of Meta Superintelligence Labs, the company has manufactured a limited run of 5,000 Muse Home Link units. Meta is giving these devices away to interested users. A waitlist has been opened for individuals hoping to secure one of the gadgets, with shipping expected to begin sometime this month.
What it means for developers
For the developer community, Meta’s decision to open-source the Muse gadget framework represents a significant shift toward accessible physical AI integration. Instead of relying solely on closed, proprietary consumer hardware, developers now have the SDKs required to map an AI agent's capabilities directly to physical inputs and outputs, such as buttons, sensors, and actuators. The inclusion of ESP32 and Raspberry Pi support ensures that the barrier to entry remains low, utilizing inexpensive microcontrollers and single-board computers that many developers already own.
This open ecosystem relies heavily on community-built skills to expand what the Muse agent can achieve in a physical environment. As developers begin building these custom integrations, managing various AI models and APIs becomes an essential part of the workflow. To streamline this process, developers can experiment with top AI models cheaply through one API at https://apixoai.online, which provides pay-per-token access to major models like Claude, GPT, Gemini, Grok, and DeepSeek using a single API key.
Ultimately, this release allows developers to explore the boundaries of ambient computing and physical AI interfaces. By combining open-source SDKs with community-created skills, developers can customize how an AI agent interacts with the real world, turning everyday electronics into responsive, intelligent tools.
Source: Meta open sources code to let you make Muse AI gadgets — The Verge AI. Written by the Apixo team from that report.
One key for Claude, GPT, GLM, DeepSeek and more. Pay per token with crypto.
Get your API key
