1076 musecases built now with Muse

Ornith does really well. TielCoder (https://llm-bench.io/benchmarks/cmt7kp2zj002r01lcmpchvlko) might be even a bit better in coding. Will give it a try soon. Details of the comparison see here: https://llm-bench.io/compare/runs?runs=cmt6ecf8g000001p45vwzux53%2Ccmt6ergk5000701p41hqdyy78%2Ccmt6f2oob000e01p49o9592cb%2Ccmt6fqddm000l01p4l1vm7skd

dp

@dpfebo

i asked @Muse to find me ways to save money and it singled out my $5/mo Poke sub to cancel LOL. i thought ppl were lying

Erik Lammerding

@Lammerding

@muse found me a car ferry from Croatia to Italy. Saved me $2200 in drop-off fees. Booked/paid the ferry, bonus - extracted information like license plate, car model, etc, from the rental agreement, confirmed I was insured for the voyage. 🙌@alexandr_wang @natfriedman

HolaClaw tested Muse Glimmer on base M3 and M4 Macs: it fits in 24GB of RAM but generates at 4.3 tokens per second.

@obaid

@obaid

Agent plugin and stdio MCP server for Resemble AI media authenticity that works with Muse: run investigations on public URLs, submit deepfake detect jobs and ask follow-ups on reports.

WTF Code uses Muse Spark 1.3 Contributor Free through OpenCode to build an interactive project from scratch, testing UI, animation, debugging and multi-step development.

@accretional

@accretional

Unofficial knowledge base and tools for Meta's Muse Spark, starting with a root-cause write-up of Codex tool-calling failures with Muse Spark 1.1.

elie

@eliebakouch

extremely exciting to see meta getting back into open weight models with a 30B dense first, and soon muse spark 1.2 they used knowledge distillation from muse spark, architecture wise it's similar to gemma 4 (which is llama 3 + swa (again!) + vision encoder), with scale free QK

Loyc C.

@loyCossou

Today I provided a Google Analytics report and asked Muse to change the figures and adjust the other details, charts etc... It did it. Claude and Gemini refunded.

Hugo Barra

@hbarra

Every @Muse partnership we've announced so far; all these connectors are either live or coming very soon 🧵 👉Reply to this thread: what other Muse connectors do people want?

@TheStreamCode

@TheStreamCode

Hermes Agent plugin that adds a muse-code provider reusing your Meta login, so Muse Spark runs on your Muse Code subscription instead of per-token API billing.

My fun weekend project was to try to make the new Muse Glimmer 30B work with a longer context, deciding to go for 512k first. I had expected the usual YaRN shenanigans and maybe a LoRA. I couldn't have been wrong more. Upon closer look, Glimmer turned out to be rather unusual architecturally. The thing that make long-context adaptations painful in other models, full attention layers with token position encoding, it simply not there. Instead, only 2048 tokens-wide SWA layers have RoPE, and full GQA attention layers have no position encoding at all. It appears the model is trained to work with long-distance token relationships inferred from the context and SWA layers. It's a rather bold architecture bet, but it seems Meta managed to pull it off. As a result, the model architecture appears to be uniquely suited for context extension by simple mechanical means. To change model context length from stock 128k to, say, 512k, you need only to change “max_position_embeddings” config setting from 131072 to 524288. What confuses other models, like Qwen3.5 family, Glimmer just takes into its stride. I spent close to 70h of compute on DGX Spark to test stock model with extended context on a

Alex Cornell walks through how his Muse buys movie tickets, plans family weekends and helps his chess game, covering the chat tab, feed, proactive ideas, goal tracking and library.

DHH

@dhh

I had Muse Code convert a TanStack version of our new site to Astro. It did a flawless job. And all I managed to spend was 20 cents!! I think maybe this token stash from @finkd and @AIatMeta is going to last longer than the sun has gas left to shine 🌅

Stackademic covers the architecture of Muse connectors, how to design connector actions, prompt-injection risk, and whether building one is worth it now that the platform is open.

@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.

Mixed-precision NVFP4/MXFP8 checkpoint of Muse Glimmer packed for SGLang, keeping v_proj, down_proj and lm_head at MXFP8.

Fei Xia

@xf1280

Fun visually-grounded 3d visualization with Muse Spark - by asking the model to generate a 3d visualization of how much each component cost on a xbox 360 motherboard (and put the bar on the component).

@Rutvik1337

@Rutvik1337

A gallery of 100 single-file HTML pages one-shotted with Muse Spark 1.3 Contributor, with a searchable catalog page and inline previews on GitHub Pages.

Sree

@srikanthvaluri

A realistic 3D model of a BMW S1000RR superbike in Three.js Fable 5.1 VS Muse Spark 1.3

Christian Van Der Henst✨

@cvander

Muse just got me tickets navigating a Basque shopping cart. I’m giving meta the lead in the game of agents as of today. 👏

Artificial Analysis

@ArtificialAnlys

Last week the Intelligence Index vs Cost Pareto frontier moved out substantially. Claude Fable 5.1, Muse Spark 1.3, and GPT-6 Astra each set a new point in efficient intelligence Link to analysis: artificialanalysis.ai/#intelligence-…

Morgan

@morganlinton

Okay, finally finished my Muse Spark 1.3 benchmark. This ended up being the longest-running benchmark I've ever done at @VulcanBench and it definitely looks like Muse has some serious issues at lower effort levels. I was able to run Astra through my v4 eval suite across every

+1

Mostly Borrowed Ideas

@borrowed_ideas

Built a little game with Muse called Hindsight Capital. Eight anonymized real historical companies; you read the financials as they were at the time, decide to invest or pass, then live through the actual crisis that came next. You then see how you did. muse.ai/s/stock-market…

Boz

@boztank

Very excited about the launch of @Muse today. I’ve been using it internally for months and I am hard pressed to think of any product that I’ve come to rely on more in such a short period of time. I have it linked to my email, calendar, and credit cards. I use it to help me plan

AI/ML API

@aimlapi

Muse Spark 1.3 vs 1.2: sculpt viking figurines @AIatMeta dropped Muse Spark 1.3 today — we ran it against Muse Spark 1.2 both models got the same brief: three collectible 3D figurines — a viking helmet, a diamond-studded axe, a longship with a crew — one self-contained HTML

@TheStreamCode

@TheStreamCode

opencode plugin that bills Muse Spark usage to a Muse Code monthly subscription through a Meta device-code login instead of a pay-as-you-go API key.

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

ollama

@ollama

Ollama already support the Muse Code harness out of the box? You can try it with models via Ollama (local and cloud): ollama launch muse

@ArshansGithub

@ArshansGithub

An OpenAI Responses-compatible shim that serves the Muse assistant as a stateless HTTP model backend for Claude Code via CLIProxyAPI, one model turn per request.

AdaptlyPost walks through connecting its scheduler to Muse as a custom connector: give Muse the public OpenAPI spec and docs, then paste a bearer token into Muse's secure credential prompt.

Peter Steinberger 🦞

@steipete

CodexBar learned a few new tricks in the last few weeks! TypeSafe, Nous Portal, Muse Code, CodeRabbit, Replicate, HuggingFace, Pi, Helmcode, v0, Charm Hyper, GitKraken AI, Bifrost My ambitions for this app REALLY outgrew the app name. (Oh and these keychain alerts are no more)

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.

@JustinAllen03-stack

@JustinAllen03-stack

A Muse skill that lets you prod friends' Muse agents with a designed speech pattern, like a Facebook poke: the imprint shows in their next replies, then fades.

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!

@danny-hines

@danny-hines

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.

Prakash

@8teAPi

My Muse just reported @vidIQ to the FTC. - @vidIQ does this 98 cent membership offer, then the next week you get hit by $49.99 - marketed to my kid, who has a small Apple Pay allowance - tried to drain it (it was already drained) repeatedly, hit the account a couple of times a

Cline

@cline

Muse Spark 1.1 just launched and it's their most capable coding agent model yet. On Terminal-Bench 2.1 it scores 80.0%, in the same cluster as Opus 4.8 (82.7%) and GPT 5.5 (83.4%). Use it in Cline with the Meta API!

Shashanka Rao

@shashankasrao

Asked my muse to book bus tickets from Bilbao to San Sebastián. It figured out my flight itinerary, figured out Amex doesn’t work, switched to my visa and got the tickets. It made a slight mistake and booked the 5:45 one. It then booked the correct one and got me a refund.

Jon ONeill

@HouseHackerJon

I’ve built this but for @Muse A community styles Creator studio Prompt and images available musecharacters.jononeill.dev Use the tag #MuseCharacterStudio And I’ll add yours to our gallery! @MattPRD have you seen any cool ones you want added? Or has @alexandr_wang ?

+3