GitHub

@youdotcom-oss

@youdotcom-oss

You.com's harness for evaluating Muse Glimmer 30B on DeepSearchQA with You.com MCP tools inside pi sessions. A custom RLM v5 extension reached F1 0.8054 on 50 tasks (0.6910 over 900x3) versus 0.50 for plain skill injection.

@evangit2

@evangit2

A guide and tooling for pointing Muse Code's meta provider at any OpenAI-compatible gateway with API-key auth and no Meta login, including workarounds for 1.0.1's bearer-withholding change.

@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.

@mattsta

@mattsta

A translating proxy that lets the muse coding agent run on OpenRouter despite its compiled-out provider support; the included verifier drives the real muse binary and passes 19/19 checks.

@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.

@newjordan

@newjordan

A tested Muse Glimmer 30B Q4_K_M serving package for Intel Arc Pro B70 with full 131k context, reporting 19.0 tok/s decode at 129k cached and 503 tok/s full-context prefill.

@raksix

@raksix

A documented setup that runs Muse Spark 1.3 Contributor inside Claude Desktop on macOS through a small Node proxy that translates Anthropic requests to OpenCode Go's OpenAI-style API.

@Satgoy152

@Satgoy152

A project that fine-tunes a DSpark speculator for Muse Glimmer 30B on on-policy coding and agentic traces to raise acceptance length on agentic workloads, evaluated with Terminal-Bench.

@bentedesco

@bentedesco

A shared Socket Mode transport between Slack and Muse bots: one listener daemon appends Slack events to a JSONL log, a CLI posts replies back, and each bot runs its own consumer with no public HTTP endpoint.

@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.

@lobanov

@lobanov

An effort to make Muse Glimmer 30B actually use a 512k-token context (4x native) as a ~17GB GGUF in 32GB VRAM, trained on DGX Spark and evaluated with RULER-style retrieval tests.

@fortun8te

@fortun8te

ocodex fans out Muse Spark 1.2 Contributor workers on decomposable coding work while one paid supervisor audits every claim, with crash checkpoints, heartbeats and a machine-readable ledger.

@Twilight0

@Twilight0

Packaging for Meta's Muse Code on Arch Linux (AUR) and Android Termux ARM64, adding AVX2 emulation for older CPUs, a TUI session manager and multi-agent MCP sync.

@karimkfoure

@karimkfoure

An OpenCode plugin that ports Muse Code's subagent coordination core: durable child workers, a ledger mailbox and admission control, so subagents survive crashes and respect capacity.

@luckeyfaraday

@luckeyfaraday

An unofficial loopback shim that lets Meta Muse Code use OpenAI Responses APIs, OpenRouter, Codex OAuth and the official Claude Code CLI, switchable from Muse's /model menu.

@aminamos

@aminamos

Four graphical frontends for Muse Code (Tauri apps for Windows and macOS, Expo apps for iOS and Android) plus a Deno relay, so every run executes through muse on the subscription login.

@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.

@r0b0tlab

@r0b0tlab

Reproducible native NVFP4 serving of Muse Glimmer 30B on one DGX Spark (GB10) with unmerged vLLM support: about 10.3 tok/s single-stream versus 4.2 for BF16, 52.5 tok/s at c16, and 131K context checked with needle-in-a-haystack tests.

@akshat12

@akshat12

A Herdr integration that uses Muse Code lifecycle hooks to show muse panes as working, idle or blocked (approval needed) in Herdr's sidebar, with no Herdr fork.

@MiaAI-Lab

@MiaAI-Lab

A gallery of 100 self-contained generative-art, physics-toy and typography pages generated with Muse Spark 1.3, each shown next to its original prompt.

@chasko-labs

@chasko-labs

Field notes on Muse Spark, a local Glimmer delegate and the Muse Code CLI, covering setup, skills hygiene, an MCP fleet and operational lessons from a ROCm box.

@ALeksandr13254

@ALeksandr13254

A fork of NemoAgent that swaps the LLM layer to OpenCode Go models, defaulting every role (dialogue agent, executor, router) to Muse Spark 1.3 Contributor with a per-role reasoning level.

@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.

@mahdi-salmanzade

@mahdi-salmanzade

A static teardown of Muse 3.0 for macOS plus Android and iOS builds, documenting shipped tools for iMessage, WhatsApp, Mail, screen control, background sync and a bundled Chrome extension.

@nuocmam

@nuocmam

A same-prompt bakeoff site that starts with a playable penguin Tetris generated by Muse Spark 1.3 in OpenCode, with a fixed prompt for comparing other models.

@HarjjotSinghh

@HarjjotSinghh

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.

@sxuff

@sxuff

A pinned llama.cpp recipe for Muse Glimmer 30B on one NVIDIA GB10 that verifies Meta's official GGUFs by SHA-256 and reproduces text, tool-call, coding, vision and throughput checks.

@xhluca

@xhluca

Muse Code OpenRouter is a small local adapter that lets the Muse Code harness run any meta/muse* model through an OpenRouter key instead of a Meta login.

@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.

@schererstefan

@schererstefan

glimmer-cli is a local TypeScript CLI for Muse Glimmer 30B and Muse Spark 1.2 via Ollama, with stubbed tools and a reproducible tool-use eval harness.

@evangit2

@evangit2

A pure-stdlib Python proxy that exposes Meta API access to Muse Spark through OpenAI-compatible endpoints for tools like OpenCode and Hermes, with no muse CLI required.

@GGulati

@GGulati

A personal software factory built on Muse agents and Erlang/OTP principles: a markdown backlog goes in, and each run takes one item through planning, dual review, TDD, code review and verification.

@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.

@SoundDeal

@SoundDeal

dealscan is an open-source agent built on Muse Glimmer 30B that reads producer, distribution and publishing agreements, extracts the payment terms and flags risky clauses in a markdown and JSON report.

@SecretLUL

@SecretLUL

Muse Code Remote is an open-source web UI and outbound WebSocket relay that lets users drive their terminal Muse Code agent from any browser without opening ports.

@kengzzzz

@kengzzzz

An installer for a muse profile in OpenAI Codex plus helper binaries, including a Meta device-code login helper, so Codex can run on Muse without the muse binary.

@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.

@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.

@latekaapi

@latekaapi

A native macOS window for Muse Code that drives muse serve over MSP and renders approvals, questions, plans, todos and tool output as interface elements instead of terminal text.

@ryangu00

@ryangu00

A measured deployment report of Muse Glimmer 30B NVFP4 with DFlash on a single Dell Pro Max GB10, where it posted top vision and SRE-ops scores but failed five deployment gates against DeepSeek V4 Flash.