A desktop app for Muse Code on macOS and Windows with projects, git worktrees, subagents, MCP, a diff review panel and opt-in computer use that lets the agent see the screen and use apps.
GitHub · Coding & dev tools★ Pick· ★ 2
9 builds · page 1 of 1
Your product
Sponsored
Put your logo, a line of copy and an image right here, between the builds Muse developers come to read. Same size as a post.
Put your product here
Shown every 12 builds · on every catalog page
A self-hosted mini arcade cabinet on a Raspberry Pi that generates SNES-style games from a player photo and a voice prompt, using Muse Spark to judge art and Muse Image and Muse Voice Transcribe for assets and input.
GitHub · Games & 3D★ Pick
Sparkade
Helicon is an open-source desktop and web app that wraps Meta's Muse Code CLI in a Codex/Claude-style interface, grouping sessions by project with history, resume and diffs on Windows, macOS and WSL2.
GitHub · Coding & dev tools★ Pick
Helicon desktop app for Muse Code
Samuel Alexander ran Muse Glimmer 30B entirely on a Qualcomm Dragonwing IQ-9075 board for zero-shot PCB defect inspection and tool calling, measuring 21.6 GB resident with full 131K context and 2.84 tokens/s generation.
GitHub · Local & open models★ Pick
Muse Glimmer 30B on a Qualcomm Dragonwing board
Custom firmware and a Go server that turn an M5Stack StackChan into Tarquin, a voice-driven robot butler with wake word, face tracking and on-device speech, using Muse Spark 1.3 via the Meta Model API as its brain.
GitHub · Local & open models★ Pick
Tarquin: StackChan robot butler on Muse Spark
Dilmer Valecillos converted a minigolf prototype to VR for Meta Quest 3 using Muse Code with the Muse Spark 1.2 Contributor model, the Unity CLI and the MetaVR CLI, and published the plans and prompts.
GitHub · Games & 3D★ Pick
Minimal Golf VR converted with Muse Code
A vLLM-XPU and DFlash recipe for Muse Glimmer 30B on a single Intel Arc Pro B70, reporting 278 aggregate tok/s across eight clients and an 840.8 tok/s burst peak at concurrency 96.
GitHub · Local & open models★ Pick· ★ 1
Muse Glimmer on one Arc Pro B70
A hands-free interface that turns Meta AI glasses into a voice control surface for Muse Code on a Mac: assign a task, walk away, hear progress, interrupt and approve sensitive steps.
GitHub · Coding & dev tools★ Pick
MuseGlass
Refusal-direction ablation on Muse-Glimmer-30B that cut refusals from 128/150 to 3/150, adding an agentic-safety evaluation and publishing bf16 and GGUF uncensored weights.
GitHub · Local & open models★ Pick· ★ 1
Muse Glimmer abliteration
About this shelf
This shelf lists about 125 GitHub repositories you can clone and run. Most are tools for developers working with Muse Code, Muse Spark or Muse Glimmer.
On the Muse Code side there are desktop and mobile GUIs, a VS Code extension, packaging for Arch Linux and Termux, and gateways that point the harness at OpenRouter or any OpenAI-compatible endpoint. The muse_spark Ruby gem is a zero-dependency client for the Model API, and Meta's own Model API cookbook is here too.
Muse Glimmer repos are mostly serving recipes: a Runpod worker, a DGX Spark launcher, a llama.cpp Makefile for macOS and a setup that runs it on free Kaggle T4s. Beyond tooling, there are finished projects like Mini-Muse, a research agent that waits for approval before writing its report, and dealscan, which reads music contracts with Glimmer. Others are playful, like Sparkade, a Raspberry Pi arcade cabinet, and ZuckLM, an overengineered parody. Check each repo's license and activity before you depend on it.
Frequently asked
+Is there an SDK for Muse Code?
Yes. Meta publishes a TypeScript SDK, @muse-code/sdk, for building clients that drive Muse Code sessions. Several repos here use it.
+How do I serve Muse Glimmer with vLLM or llama.cpp?
Repos on this shelf include working recipes for vLLM, SGLang and llama.cpp on NVIDIA, AMD, Intel and Apple hardware. Meta's Glimmer post also covers vLLM, llama.cpp and ExecuTorch.
+Can I use Muse Code with other model providers?
Community gateways let the Muse Code harness talk to OpenRouter or any OpenAI-compatible endpoint, and Ollama shows it running with local models via ollama launch muse. These are community projects, not official support.
ChatForm
Tgmlabs