GitHub

@jason-snell

@jason-snell

windows-cua is a native C++ Win32 port of Meta's macOS computer-use agent that drives Muse Spark 1.1 through the Responses API to see and operate a real Windows desktop.

@codemarc

@codemarc

A VS Code and Cursor sidebar chat that drives Meta's Muse Code CLI through muse exec --json, keeping Muse as the agent harness; its build is described in the post 'Inception: A Muse Inside Muse'.

@LilMuh

@LilMuh

Since Muse for Mac ships only for Apple silicon, this small service lets Muse's cloud VM screenshot, click and type on an Intel Mac, compressing each 5K frame to about 150 KB and handling Retina coordinate scaling.

@TMTrevisan

@TMTrevisan

A self-healing watchdog pattern for AI agent VMs: byte-exact restore caches in persistent storage, sentinel probes, no-clobber atomic restores, and verified heals. When the VM's root filesystem is rebuilt with pieces missing (Python stdlib, timezone data, Node), the watchdog restores them in minutes and reports only repairs and failures. Includes an AGENTS.md so any agent can set it up.

@MiaAI-Lab

@MiaAI-Lab

A one-script vLLM setup that serves the roughly 19 GB NVFP4 Muse Glimmer 30B with its vision encoder kept, DFlash speculative decoding using the official drafter head, and up to 256K context on GB10, RTX 5090 or RTX PRO 6000.

@cccrust

@cccrust

A computer system including an OS, compiler and CPU written in Rust and Verilog, designed with Meta's Muse Spark 1.3.

@GordonWei

@GordonWei

An OpenAI-compatible /v1/chat/completions server that runs Muse Glimmer on Apple Silicon through mlx_vlm while LM Studio's bundled MLX runtime can't yet load the architecture.

@say4n

@say4n

A fork of DeepSeek's DeepSpec that trains a fresh DSpark speculative drafter for Muse-Glimmer-30B in place of the shipped DFlash drafter, with the full data-to-eval pipeline working on GPU.

@johnhalloran321

@johnhalloran321

Scripts that run Muse-Glimmer-30B with vision and tool calling on a 32GB M2 MacBook Pro via llama.cpp and Metal, without admin or sudo access, pulling Meta's official GGUFs.

@ND-DAC-DOME

@ND-DAC-DOME

A test bed comparing Muse-Glimmer-30B against Qwen3.6-27B and Qwen3.8-27B under identical settings; with 32k-token budgets the three were about even (MMLU-Pro 82/82/80%).

@daum110715

@daum110715

A Three.js, Vite and TypeScript survival-lite voxel game built with Muse Spark, with infinite terrain, crafting, hunger, day-night cycle and zombies.

@hoziertom44-arch

@hoziertom44-arch

A Python bot for Binance USDT-M futures, built with Meta AI's Muse Spark, that trades ETH inversely when BTC and ETH show strong opposite 9/21 EMA trends on 5-minute candles.

@rickyzzzzz

@rickyzzzzz

A controlled local benchmark on an M1 Max comparing Muse Glimmer 30B with Qwen 3.6 35B and Qwen 3.8 27B on tool calling and data-science tasks; Glimmer passed 24/30 versus Qwen 3.8's 30/30.

@m5it

@m5it

A four-in-line game built with the AIIA framework, where the plan came from the author's own model and the build then switched to Muse Glimmer running on 16 GB of VRAM.

@dilmerv

@dilmerv

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.

Anonymous

github.com

An open-source file bridge that gives Muse real read/write access to your Windows PC: a lightweight local Python server (Bearer-token auth, directory whitelist, path-traversal protection) exposed via Cloudflare Tunnel, so the agent works with your actual files instead of chat attachments.

@shelajev

@shelajev

A Docker Sandboxes kit that runs Meta's Muse Code CLI in an isolated sandbox, allowing network access only to the Meta services needed for install, auth and model requests.

@krtarunsingh

@krtarunsingh

An experiment running Muse Glimmer 30B Q4_K_M via llama.cpp on an RTX 4060 laptop with 8 GB VRAM, testing autonomous Python bug fixing, tool-failure recovery and multimodal invoice extraction.

@TrevorS

@TrevorS

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.

@EtienneLescot

@EtienneLescot

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.

@AIwork4me

@AIwork4me

A reproducible RDNA reference that adapts MI-series ROCm recipes to run Muse-Glimmer-30B on Ryzen AI (Radeon 8060S) hardware, measuring 2.2–2.5x single-stream speedups from DFlash.

@dp1x

@dp1x

A small local proxy between Grok Build and OpenCode Zen that fixes muse-spark-1.2-contributor-free streaming, with a technical report of protocol captures and root cause.

@Abhishektenneti

@Abhishektenneti

A reproducible record of running the 17GB Muse Glimmer 30B GGUF with llama.cpp and Metal on a 24GB M4 Pro MacBook Pro, with notes on mistakes, fixes and how local inference works.

@alpharomercoma

@alpharomercoma

A reproducible setup serving Muse Glimmer 30B on one AMD MI300X with a custom 11 GB vLLM 0.28.0 ROCm image, exposed as an authenticated OpenAI-compatible endpoint and driven from the pi CLI.

@saipreetham99

@saipreetham99

MdChat is a native macOS Markdown previewer and vim-keyed editor with an AI side panel that answers questions about selected blocks and rewrites them behind a diff, using Gemini or Muse Spark.

@nisten

@nisten

A single static HTML page that renders every weight tensor of Muse Glimmer 30B in 3D, sized by bits on disk, with educational notes on each layer.

@MrShitFox

@MrShitFox

A localhost compatibility gateway that lets the native Muse Code harness run on OpenRouter's muse-spark-1.2-contributor, rewriting only the model name and never falling back silently to another model.

@mitchallen

@mitchallen

A Makefile that downloads the three Muse Glimmer 30B GGUFs and builds and serves llama.cpp on Apple Silicon, automating a scriptable.com walkthrough.

@tanishq-dubey

@tanishq-dubey

A reproducible Apple Silicon harness that runs six fixed quality tasks against MLX quantizations of Muse Glimmer 30B and records scores, tokens per second, peak memory and load time.

@cneuralnetwork

@cneuralnetwork

smol-muse-glimmer scales Muse Glimmer's language backbone down to a 51M-parameter model and trains it on TinyStories, reaching validation cross-entropy of 1.8127 at step 5,000.

@vasyl-stanislavchuk

@vasyl-stanislavchuk

A separate launcher with its own config profile that runs Claude Code's interface on Meta's muse-spark-1.3, for comparing models on identical work or using a Muse Code subscription.

@MoheetBrain

@MoheetBrain

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.

@Fangyuan025

@Fangyuan025

Chaty is a private offline desktop app built on Rust and llama.cpp that runs Muse Glimmer and other open models locally with a coding agent, RAG knowledge base, deep research and voice.

@Srimi1

@Srimi1

A hybrid harness with a claude-muse launcher that runs Claude Code on Meta Model API Muse Spark models, plus a /talk broker for structured exchanges between Claude Code and Muse Code terminals.

@jjakemaness

@jjakemaness

TerMuse shows the live terminal and an interactive browser of the machine a Muse agent is working on, side by side, so the user can watch and type or click in the same session.

@wonder-soft

@wonder-soft

A benchmark that tests whether Muse Glimmer 30B on a single RTX 5090 works as an OpenCode backend, using the same tasks as earlier DeepSeek and Qwen runs; first results show 18/18 episodes with zero malformed tool calls.

@Alphaxalchemy

@Alphaxalchemy

A ~90-line zero-dependency Node forwarder that lets OpenAI Codex switch between GPT and third-party models such as Meta Muse Spark just by model name.

@Codys12

@Codys12

A correctness-first bring-up of Muse Glimmer 30B on a single Tenstorrent p150 card, with paged KV cache, native DFlash speculative decoding and an OpenAI-compatible server.

@willsigmon

@willsigmon

Calliope is an unofficial, independent native macOS client for Meta's Muse, shipped as a Developer ID-signed, notarized DMG with Sparkle auto-updates; five releases went out between Sept 13 and 16.

@Wraient

@Wraient

A Go reverse proxy with an embedded dashboard that lets Claude Code and OpenAI/Codex clients use muse-spark models through a Muse Code subscription, authenticated with the muse login credential.