1093 musecases built with Meta Muse

@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.

NetworkCoder runs Muse Glimmer 30B on an RTX 3090, measures speed and VRAM, and gives two agent harnesses the same model, endpoint, project and prompt to compare results.

Better Stack runs both new 30B models on autonomous coding, Adobe Premiere control via MCP and parsing a 100+ page SEC filing.

jaidha

@jaidharo

Told @muse about my flight this morning. It compared uber vs airport parking, bought a Groupon to get it half off, booked the reservation for me via computer use, then told me what time to leave. Wild

@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.

David Singleton

@dps

Podcasts work with scheduled tasks so you can have your Muse make you a new episode every day. I’ve been listening to AI news curated by my Muse while commuting to the office for the past few months and it’s great to timeshift things I want to learn more about to a Podcast I can

@siddicky

@siddicky

An oh-my-claudecode-style gated pipeline for the Muse Code CLI, from deep-interview to verified code, shipped as a native Muse plugin manifest with a skills fallback.

Built an open-source version of the Muse agent app which can be used with any model provider, run privately with local models. Please give it a try and reach out for any feedback ✌️ https://github.com/CelestoAI/celesto/tree/main/open-muse

artificialanalysis.ai

artificialanalysis.ai

Artificial Analysis puts Muse Spark 1.1 at 51 on its Intelligence Index, 8 points above 1.0, and calls it cost and token efficient versus peers.

@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.

@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.

manufact.com

manufact.com

Pietro Zullo walks through submitting a hosted MCP server to the Muse connector platform: the three-step form (overview, technical specs, review) and what Meta's functional and security review checks.

@kyl3kan3

@kyl3kan3

A Muse connector for small HVAC and plumbing shops that lets the agent quote a visit, hold a slot, book the job, send a deposit link and check status via an OpenAPI spec and llms.txt rules.

@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%).

dev.meta.ai

dev.meta.ai

Meta's post on Muse Code exiting beta with inter-session messaging, parallel-agent workflow orchestration, rewind, a TypeScript SDK and three subscription tiers.

Siamese Cat Dev pits Muse Spark 1.3 against Claude Fable 5.1 on a browser OS, a Call of Duty-style shooter, a neon arena shooter and a Mario Kart-style racer.

@sanjay3290

@sanjay3290

ACP adapter that bridges Agent Client Protocol clients such as Zed to Muse Code via the Muse Session Protocol and muse serve.

Hey Folks, I've been making quants for a while - recently I took a short break to get into hardcore research (submitted my first EMNLP paper during it!). Along the way, I built up a little arsenal of quant-optim techniques: everything from novel, paper-pending tricks to some genuinely sick tensor-mapping algos. I threw some of the secret sauce into the newly released Muse Glimmer 30B (META IS BACK!) and compared it to several OGs. I'm honestly shocked by how it never loses to any quant out there in every single VRAM class! One of the coolest ones is my Q8 quant, it is smaller than UD-Q8_K_XL and 21% closer to BF16. Full methodology is on the card - eval setup, CIs, held-out slices, the lot. Happy to answer questions in the comments. Model: https://huggingface.co/AaryanK/Muse-Glimmer-30B-GGUF I still had headroom left but ran out of compute credits :( Being a solo undergrad sophomore, I can't exactly spend H100 money that often, which is why the "hopefully" in the title :) I'm looking for internships in AI agent orchestration and model inference. If this work looks relevant to your team: linkedin.com/in/theaaryankapoor I plan on doing a write-up soon to describe some of the

@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.

@spinespine

@spinespine

VS Code extension that adds Muse Spark 1.3, 1.2, 1.1 and Contributor variants to the Copilot Chat model picker with a Meta API key, published on the Marketplace and Open VSX.

research.meta.ai

research.meta.ai

Meta's engineering write-up on Muse security: isolated VMs, a separate Sentinel permission authority, credential surrogation and layered prompt-injection defenses, with bug bounties up to $300,000.

RedHatAI

RedHatAI

Red Hat AI's INT4 weight-quantized Muse Glimmer 30B.

After noticing that it is ranked among MUCH larger frontier models in the EQ-Bench Creative Writing benchmark and the Hemingway-bench, I decided to give it a try and was very impressed. I didn't do very formal testing, but I did ask it to emulate the style of several different writers, including Henry Miller, David Sedaris, and Stephen King, and it produced passable prose that actually made me laugh in a couple of cases. The paragraph below is the results of the prompt "produce a humorous paragraph in the style of David Sedaris." (first try, not cherry picked) I recently tried to be a better person and started composting, which mostly means I now have a small, damp science experiment in my kitchen that my mother calls “the smell of your future.” I bought a countertop bin with a charcoal filter, as if that would fool anyone, and I’ve taken to narrating my food scraps to myself — “Goodbye, avocado skin, you were a mistake” — while my husband watches from the doorway with the concerned expression of a man who has just realized he married a woman who talks to garbage. The city sent a pamphlet about proper composting, and I read it the way other people read horoscopes, underlining th

lmstudio-community

lmstudio-community

LM Studio community highlight GGUF quants of Muse Glimmer 30B.

Infinite Improbability

@v01dp1r4t3

Today @Muse shopped for a new garage freezer, got the best price for my required specs matching it's replacement, ordered it, kept track of the delivery, then filled out and submitted the registration. I watched every step of the way redundantly, had to enable a few more things

ChrisUniverse 🗽

@ChrisUniverse

January 1st, 2026. I wrote down “Make Faceless YouTube & TikTok channel” 9 months later, I still never got to it! 🤦🏻‍♂️ Today with @Muse I created 6 accounts: Gmail, YouTube, TikTok, Snapchat, X, IG & now FB in under 2 hours! This feels like AGI. The main benefit of Muse is h

+1

karthk

@thekarthk

Day 2 with Muse and I'm sold. It rebuilt my boys trip page for October - dates, routes, the works - and even found a foliage drive I hadn't thought of. Then it set up my Instagram Content Studio with a full batch of trip ideas, captions, and shot lists ready to go. Then FPL:

Plant

@plantmath1

Same theme - I told @Muse to move one of my website domains from GoDaddy $GDDY to Cloudflare $NET. Something I've been meaning to do for years but too lazy. Saved some $ too.

Sheel Mohnot

@pitdesi

Muse has been good, surprised that this happened I asked it where to go for dinner, it recommended Bar Agricole, and then tried to book it for 7 mins, but couldn't get through. The only problem is that Bar Agricole has been closed for 2 years!

Anukshi Mittal

@anukshi13

asked Muse what i should do this weekend. it researched, gave me ideas, made the plan, and set reminders. very into it!

muse.ai

muse.ai

Meta's developer portal for Muse connectors: describe a connector, submit it for functional, security and legal review plus end-to-end testing, and get listed in the Muse directory.

burtenshaw

burtenshaw

Ben Burtenshaw's Gradio agent runs Muse Glimmer on an Inference Endpoint with read-only Hugging Face MCP tools to search and inspect Hub models, datasets, Spaces, docs and papers.

duffel.com

duffel.com

Duffel's travel API is embedded in Muse so users can search live flight inventory across 500+ airlines, book, and manage trips including cancellations.

Mark Zuckerberg

@finkd

Today we're also opening the weights for Muse Glimmer, a great 30B parameter dense model that can run locally. Soon we'll also release the weights for Muse Spark 1.2, our latest foundation model. Meta is a strong supporter of open source and I'm proud of these releases. Congrats

STARTUP HAKK tests Muse Spark 1.3 and argues the harness, tools and context around a model matter as much as the model, pitching their OpenMonoAgent harness.

@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.

trycodus.com

trycodus.com

Codus reads the three benchmark charts Meta published for Muse Code and notes Claude Opus 5 wins all three, including Meta's own internal eval.

Abhiraj Butala

@abhirajbutala

Asked my @muse to find the items from a saved IG reel. It "watched" the reel, matched everything across Amazon & Etsy, and loaded my carts with a few solid options per item. Spared me the research grind entirely.

Meta Developers session on what Muse Spark's act-on-perception multimodality unlocks across code, physical action and video workflows, plus Muse Voice Transcribe.

AI Coding Daily re-runs its Muse Spark 1.3 tests using the max reasoning level inside Muse Code.