Assistants & chat
Muse Gadgets
Meta's open-source SDKs and firmware for building ESP32 and Raspberry Pi devices that connect to its Muse assistant.
What Muse Gadgets does
Muse Gadgets is a set of open-source device SDKs and firmware from Meta for building your own hardware that connects to Muse, Meta's assistant. You program an off-the-shelf ESP32 board or set up a Raspberry Pi or other Linux machine, then wire in screens, buttons, speakers, microphones or sensors.
There are two SDKs. The ESP32 Device SDK handles displays, audio in and out, and other sensors. The Linux Device SDK lets you add your own commands, with sysadmin chores and a Home Assistant setup given as examples. Every gadget needs an SDK token from gadgets.muse.ai before it can pair, and pairing happens in the Muse app on iOS or Android after you turn on Developer mode. Each SDK folder includes a README and an AGENTS.md file for coding agents.
The site lists project ideas with ready device configs: a Waveshare round AMOLED touch screen, M5Stack StickS3, Seeed reTerminal E1002 e-ink display, AiPi Lite, an ideaspark ESP32 with a 1.9-inch screen, Home Assistant Voice Preview Edition and Raspberry Pi 5. Other companies make and sell these boards. A separate Muse Home Link device is offered free to Muse subscribers in the United States, one per subscriber.
The code is Apache 2.0 and provided as-is, and the site warns that tinkering can brick boards or void warranties. It suits hardware hobbyists who already use Muse. The gadgets site does not state what a Muse subscription costs.
- Put a morning briefing, reminders or a shopping list on a color e-ink display.
- Build a push-to-talk desk device that speaks Muse's answers and shows pictures.
- Turn a Raspberry Pi into a gadget that runs your own commands, such as Home Assistant actions.
- Add a small status screen that shows what Muse is doing.
Who should use it
- Makers with ESP32 boards or a Raspberry Pi who already use Muse.
- Developers who want to extend Muse onto custom hardware.
Who should look elsewhere
- People without a Muse account, since every gadget pairs through the Muse app with an SDK token.
- Anyone who wants a finished, supported device; the code comes without warranty.
Strengths
- Apache 2.0 licence for the SDKs and firmware.
- Separate SDKs for ESP32 microcontrollers and Linux machines.
- Ready configs for several boards you can buy today.
- AGENTS.md files help coding agents work on the code.
Limitations
- Requires Muse, an SDK token and the Muse mobile app to pair.
- Muse subscription pricing is not stated on the gadgets site.
- Muse Home Link is limited to US subscribers, and the TV stick is listed as coming soon.
- Provided as-is; the site warns of bricked boards and voided warranties.
Sources
- Muse Gadgets: Open source hardware for your MuseOfficial sitePrimarygadgets.muse.ai
- github.com/facebookincubator/muse-gadget-sdkRepositoryPrimary
- github.com/facebookincubator/muse-gadget-sdk/blob/main/LICENSERepositoryPrimary
Muse Gadgets alternatives
KernelAI
Assistants & chat
An iOS and Android app that runs 53 open-weight models offline on your phone, with no account or subscription.
FreeFree tierVerified
Related open-source projects
VoiceStudio is a desktop app that runs speech AI on your own computer: it clones and designs voices, generates speech from text, dubs videos, transcribes audio and has a dictation widget. The app is built on Electron with a Python backend. Its default speech engine is k2-fsa's OmniVoice, and the feature catalog lists more than a dozen alternatives, among them CosyVoice 3, KittenTTS, MLX-Audio and IndexTTS 2.5. Transcription defaults to WhisperX, with Faster-Whisper, Parakeet, Moonshine and others available. Models are downloaded when a workspace first needs them. The project says its tools cover 646 languages, a figure that also appears in the transcription tool of its MCP docs. Beyond the desktop workspaces, VoiceStudio exposes a local API and an MCP server on port 3900, so coding agents can generate speech, clone a voice or transcribe a file. The README states that local workflows stay on your hardware, remote workers are optional and usage analytics only run with consent. Version 0.5.3 was the last release built on Tauri; current releases are Electron only, and Tauri users have to install the new app separately.
- Stars
- 61K
- Language
- Python
- License
- AGPL-3.0
- Momentum
- +16.0% 7dTrending
qwen-audio-agent is a realtime voice runtime that sits in front of a coding or task agent. You talk to a voice model, longer jobs go to a backend agent while the conversation continues, and when a task finishes its result comes back into the same conversation. The voice side is swappable. Cloud options listed in the README include Qwen Audio 3.0 Realtime, GPT-Live / OpenAI Realtime, Google Gemini Live and Doubao Seeduplex 3.0 Realtime, each needing that provider's API key. Hugging Face Speech-to-Speech and MiniCPM-o 4.5 can run locally. Backend agents connect mostly over ACP: the list covers Qwen Code, OpenCode, OpenClaw and Kimi Code, with Codex and Claude Code joining through an external ACP adapter. You can use it from a WebUI, a terminal TUI or a desktop floating orb on macOS, Windows and Linux. The README also lists parallel background tasks you can query or cancel, cross-session memory, and scheduled reminders. The package is published on npm under Apache-2.0, a technical report is on arXiv, and the repository sits in the QwenAudio GitHub organization.
- Stars
- 2.9K
- Language
- JavaScript
- License
- Apache-2.0
- Momentum
- Emerging
Ponytail is a rule set and skill collection that pushes an AI coding agent to write as little code as a task needs. It ships as a plugin for Claude Code, Codex, GitHub Copilot CLI, Gemini CLI and several other agent hosts, and as plain rules files for editors such as Cursor, Windsurf and Cline. Before writing anything, the agent works down a fixed ladder: drop the feature if it does not need to exist, reuse what the codebase already has, then try the standard library, a native platform feature, an installed dependency and a one-line answer. New code comes only after all of those fail. The README is firm that validation, error handling, security and accessibility are off limits for cutting. Its example: asked for a date picker, the agent reaches for a native <input type="date"> instead of adding a library and a wrapper component. The plugin adds commands to set the intensity (lite, full, ultra or off), to review a diff or a whole repository for over-engineering, and to collect deferred shortcuts into a ledger. The maintainer publishes a benchmark: across twelve feature tasks on a FastAPI and React template with Haiku 4.5, the README reports about 54% fewer lines of code than the same agent without the skill, plus smaller drops in tokens, cost and time.
- Stars
- 162K
- Language
- JavaScript
- License
- MIT
- Momentum
- +5.7% 7dEstablished
Agent Skills is a repository of 25 Markdown workflows for AI coding agents, covering software work from specification and planning through testing, review, performance, security, deployment and documentation. Each skill is a SKILL.md process with triggers, steps, red flags, verification criteria and common rationalizations to counter. The pack can be installed with the skills CLI or integrated with tools including Claude Code, Cursor, Gemini CLI, OpenCode, GitHub Copilot and Codex. Nine slash commands map development tasks to skills. /build auto can generate a plan and implement its tasks after one approval, while stopping on failures or risky steps. This suits teams that want an agent to follow a defined engineering process instead of relying on isolated prompts. The repository also contains four review personas, shared checklists, evaluation cases and host-specific adapters. One installation limitation matters: installing a single skill through npx does not copy the repository-level references/ directory, so links to shared checklists are unavailable unless those files are supplied another way.
- Stars
- 106K
- Language
- JavaScript
- License
- MIT
- Momentum
- +4.9% 7dEstablished