GitHub

@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.

@dominicletz

@dominicletz

A self-contained visual report comparing CursorBench 4.0 score against cost per task for Opus 5.5, Fable 5.1, Grok 4.7 and Muse Spark 1.3, where Muse Spark 1.3 Max scores 41.6% at $2.64 per task. GPT-6 points are clearly marked as estimates.

@dttdrv

@dttdrv

An unofficial native macOS client for the Muse Code CLI in Meta AI's design language, sharing sessions with the terminal so work can resume in either place.

@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%).

@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.

@meta-models

@meta-models

Meta's official recipes for building agents and coding tools on the Model API with Muse Spark 1.3, covering API basics, multi-agent patterns and end-to-end use cases via OpenAI- and Anthropic-compatible SDKs.

@cellear

@cellear

A read-only visual companion that reads Muse Code session event logs and rebuilds multi-agent sessions (a primary agent and its workers) as a live tree.

@BrokkAi

@BrokkAi

muse-acp is a dependency-free Rust bridge between the Agent Client Protocol and Muse Code's Muse Session Protocol, letting developers use their Muse Code subscription inside Zed, IntelliJ IDEA and other JetBrains IDEs.

@caicaitou001

@caicaitou001

A config and write-up that makes muse-spark-1.2-contributor via OpenCode Go work in DeepSeek Harness, fixing empty first-turn output and multi-turn thinking replay errors.

@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.

@arananet

@arananet

A CLI that opens a shop in headless Chromium to check whether an AI shopping agent can discover and act on the page, and can ask a real Muse Code agent to shop it through the official @muse-code/sdk.

@bex-co

@bex-co

muse-code-acp is an unofficial Node adapter that exposes Meta's Muse Code through the Agent Client Protocol, so it can be driven from Zed or VS Code with streaming, tool calls and MCP servers.

@cobusgreyling

@cobusgreyling

Cobus Greyling's companion repo for Muse Glimmer 30B pairs a long-form intro with an offline-first interactive lab for exploring agent loops, benchmarks and memory envelopes before downloading the weights.

@syamimhazmi

@syamimhazmi

A vim-modal multi-tab Rust TUI for coding agents where each tab is a session, fronting Muse Spark via muse serve alongside Codex, Antigravity and Grok backends.

@humbertovirtudes

@humbertovirtudes

An interactive Three.js scene that shows a stylized 'Muse Spark mind' with memory, reasoning, language and sensory regions (about 218 neurons and 340 synapses), with a live demo.

@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.

@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.

@joymadhu49

@joymadhu49

A local shim that lets the unmodified muse coding CLI run on any OpenRouter API key by translating its Responses-API-plus-extension wire protocol, so no Meta account is needed.

@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.

@AshutoshKD

@AshutoshKD

An Express-based Muse connector that books Uber rides from natural language, with routes for fare estimates and ride requests, connector auth middleware and a privacy page.

@Srimi1

@Srimi1

An experimental macOS gateway that keeps the stock Muse Code CLI in charge of the UI, sessions and tools but swaps the model connection for OpenAI or Z.ai models via a loopback gateway.

@rafaelnovaes22

@rafaelnovaes22

A hybrid FastAPI gateway where a 1-bit BitNet layer on CPU filters routine traffic and Muse Spark 1.3 is called only for sales, urgency, money or low-confidence cases; the author estimates the local filter handles about 60-70% of volume.

@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.

@nicedreamzapp

@nicedreamzapp

An architecture port adding the muse_glimmer model class (vision tower, language model, projector and image processor) to mlx-vlm, so any Muse Glimmer checkpoint runs multimodally on Apple Silicon.

@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.

@h1ddenpr0cess20

@h1ddenpr0cess20

A Muse Spark 1.1-powered terminal coding agent forked from Grok Build, with a full-screen TUI, headless mode for CI and ACP embedding in editors.

@High-Performance-AI-Lab

@High-Performance-AI-Lab

A 40-chapter book on Muser, an engine that runs Muse Glimmer on Apple Silicon Metal. It covers kquant and DFlash speculative lanes, exact KV-cache replay with kvpack, and GB10 NVFP4 prefill handed off to a Mac, with every number tied to an evidence receipt.

@mapleroyal

@mapleroyal

A local Muse Glimmer 30B vision-and-reasoning chat app for high-memory Apple Silicon Macs, running inference through ExecuTorch, MLX/Metal and DFlash with nothing persisted to disk.

@cezaronx

@cezaronx

A reference CUDA worker that serves Meta's official Muse Glimmer 30B GGUF through llama-server on Runpod Serverless load-balancing endpoints or manual Pods, exposing a real OpenAI-compatible API.

@TerryZH

@TerryZH

An unofficial uninstall utility that finds Muse Code binaries and state files, estimates reclaimable space in a dry run and deletes them only with --uninstall.

@jeperkins4

@jeperkins4

A zero-dependency Ruby client for Meta's Model API focused on the Responses API: reasoning replay across tool loops, previous_response_id state, web_search grounding and typed errors with retries.

@High-Performance-AI-Lab

@High-Performance-AI-Lab

muser is a standalone inference engine for Muse Glimmer 30B on Apple Silicon Metal, with an optional disaggregated lane where an NVIDIA GB10 node prefills in NVFP4 and hands the KV cache to the Mac.

@Aeroknight786

@Aeroknight786

A local browser GUI for an existing Muse Code install, offering a persistent view of projects, tasks, conversations, permissions, activity and working-tree changes over Muse's session protocol.

@HawgAuto

@HawgAuto

Glimmer HD Vision is an OpenAI-compatible proxy that keeps images within Muse Glimmer 30B's 4,096 visual-token limit by sending a 4K image as one overview plus four overlapping detail tiles, with an OCR/layout mode.

@HarjjotSinghh

@HarjjotSinghh

Named profiles for the Muse Code CLI: keep several logins on one machine, run two at once and let each project pick its profile. Published on npm and tested against Muse Code 1.3.0.

@kevinzhao-dev

@kevinzhao-dev

A starter script that downloads Muse Glimmer 30B, serves it with llama.cpp on an Apple Silicon Mac and connects it to OpenCode, with the server listening only on localhost.

@mjsabby

@mjsabby

An OpenAI- and Anthropic-compatible serving stack for Muse Glimmer 30B on one or two Intel Arc Pro B70s, built oracle-first with a float64 CPU reference that gates every GPU kernel.

@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.

@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.

@develate

@develate

A small PHP 8.2+ SDK for controlling the Muse Code CLI, running one muse exec --json process per turn and resuming sessions by ID.