1076 musecases built now with Muse

Alex Volkov

@altryne

Oh wow, really. I was skeptical but I gave @muse and Instinct the same task, to research tickets for a rosh-ha-shana dinner. @muse is already tightly integrated with link (native integration not just a skill) and it booked me tickets, while Instinct is still searching for the

+1

https://gitgud.io/PunishedChuckle/ChuckleMagic/-/releases

Meta's lightweight DFlash block-diffusion drafter for Muse Glimmer 30B that predicts blocks of 16 tokens per forward pass for speculative decoding.

GGUF builds of Muse Glimmer 30B all cut from the same BF16 source weights, including full-precision files.

Bijan Bowen puts Muse Glimmer through a battery of builds including a browser OS, C++ skate game, subway FPS, 3D CAD model, drum-kit sim and multimodal coding.

@Curious-coder08

@Curious-coder08

An MCP server built as a Muse connector for real-time public transit: find stops, see upcoming departures with live delays, plan simple direct trips and check service alerts.

Kartik

@1kartikkabadi1

I swear Muse Spark 1.3 is a really good model. Like I don't know if it's just my setup or something. But it just constantly surprises me. So in Synara there's a thread/agents tool where it can create new threads and communicate and manage agents. And literally always, like

+2

Zach Holman

@holman

Still really enjoying @muse. I use Things.app for all of my todos, and though it has cloud sync they (still) haven’t added an official API. I told muse to build it and a minute or two later I have ongoing todo sync from my LLM across all my Apple devices. Wild.

mihawkxxx

@mihawkxxxxx

Incredible Minecraft from muse spark 1.3 cost 10 cents

She’s been enabled in some of my Instagram DM and I can summon her in chat and she clearly signs her messages. Feels like my own Friday from the MCU and I’ve just been having fun with it. I might try again for a J.A.R.V.I.S.

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

Jon ONeill

@HouseHackerJon

@Muse can’t fix my AC (yet) But they did file a police report And they filed my insurance claim for me And they’re gonna go get me some quotes What a wild day this has turned out to be

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

Dilmer Valecillos uses Muse Code with Muse Spark 1.2 and the Unity CLI to run tests, validate changes, port a Mini Golf game to other platforms and convert it to VR.

eli

@_seemethere

Just released a pi extension to make it easier to use Muse Spark 1.1 within pi! Including easy /login behavior! You can install it with: > pi install npm:pi-meta-ai

@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.

Mostly Borrowed Ideas

@borrowed_ideas

Just built a simple but pretty useful dashboard with Muse. It goes through my trade confirmation emails and then benchmarks all of my trades against SPY performance since the trade. Buys earn positive alpha when the stock beats SPY and sells earn positive alpha when SPY beats the

Derya Unutmaz, MD

@DeryaTR_

Here is a crazy Jev @typesafeai example that I’m betting nobody has thought about: I asked @Muse from @Meta to use Jev to select the top 100 unanswered questions in immunology from 10,000 literature-grounded candidates. A few minutes later, it came back with some of the best

Unsloth's bitsandbytes 4-bit build of Muse Glimmer 30B for fine-tuning and inference.

Tried to let a Muse agent's VM query Home Assistant on a home tailnet through Muse's documented tunnel proxy; every request died with 'empty reply from server' in ~8 s, and he shares the debugging so far.

@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.

https://github.com/mvrius/bluebubbles-muse BlueBubbles server on my Mac, Muse hook polling it every ~5s. How it works: the poll driver (bash shim + Python filter) checks for new messages and filters on an allowlist of senders, 1:1 chats, and group GUIDs. A new message from an allowlisted sender wakes Muse into a side chat with the message as context. Replies go back out as normal iMessages through the Mac. Why this instead of a messaging connector: connectors need an approval tap on every send, otherwise similar could be acheived via Messenger connector. Setup: BlueBubbles on the Mac, Tailscale so the agent VM can reach it, run the installer. Repo has the hook scripts, installer, architecture doc, and skill definition. Known issues: I am noticing that sometimes Tailscale connection drops on the Mac. I found that I need to bring down/up tailscale every hour for connection to stay up. A fun example from earlier today, I updated my calendar, moved dinner with my wife by 30 minutes - Muse mesaged the Family chat and informed my wife of the change. Cool findings: - Muse has a Tailscale option, you can connect the VM it runs on in Client model with other machines running Tailscal

@mgaruccio

@mgaruccio

A vLLM-XPU and DFlash recipe for Muse Glimmer 30B on a single Intel Arc Pro B70, reporting 278 aggregate tok/s across eight clients and an 840.8 tok/s burst peak at concurrency 96.

@ezcat207

@ezcat207

A curated, source-linked catalog of 156 real things people have done with the Muse personal agent, grouped into 16 categories with every entry linked to its original X post.

@stevysmith

@stevysmith

An MCP server and skill that reports live review times for AI app, connector and plugin stores, including Meta Muse, so builders can see how long a connector submission is taking.

NVIDIA's NVFP4-quantized version of Muse Glimmer 30B.

@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.

Bull Run

@run_bull_

I legit asked muse to search every state I lived in for unclaimed money. Took about 5 minutes to find that I only had $48 of unclaimed money, but helped fill the form out and it was emailed to me by the treasury. Honestly, I Use Claude, ChatGPT, Grok, and Muse is by far the most

@kyl3kan3

@kyl3kan3

Quote-and-book API for HVAC and plumbing shops in the St. Louis metro, built so a Meta Muse agent can quote, hold a slot for 15 minutes and book a job without a phone call.

ThursdAI hosts compare daily-driver assistants, then David Pawlan, who ran 273 tests across 23 assistants for Assistant Benchmark, walks through how Muse stacks up.

Zach Holman

@holman

An oldie post from 2024, but I've been curious about the data side. I had @Muse pull in my whole angel portfolio via MCP from @signedco of ~150 startups; the interesting bit: - Startups who sent investor regular updates: 8% died - Startups who didn't send updates: 28% died

Cloud Codes tests whether Muse Glimmer on a single 24GB VRAM GPU can compete with cloud coding agents in multi-step tool-calling loops.

Pete

@petehalvorsen

Gave my @Muse Hal a task to book flights, it navigated Captcha and booked @AlaskaAir for my outgoing flight, then let me know that Chase was offering a $200 deal on @flyjsx which would make it cheaper on my return flight. Asked if that would work for me… Then Booked it.

William Geronco

@williamgeronco

I told my AI assistant @Muse to start a live chat with Verizon customer support. It did, then I went to bed. She brought my bill from $516 a month to $386. I technically only asked for it to log in and take a look at my bill but then I complained that I was paying too much. With

AICodeKing tests Muse Spark 1.3 and Gemini 3.8 Flash on frontend, 3D, SVG, maths and agentic coding, and flags file-overwriting issues.

@vstaln

@vstaln

Copyable block of the engineering conventions Muse Spark was co-trained with. Per the README, in Cline's harness it cut a real bug fix from 19.7M tokens, 49 min and $7.69 to 7.2M tokens, 24 min and $3.25.

Common Thread Collective's playbook for brands selling through Muse via Shopify: audit product data for agent readability, optimize Shop Pay conversion, build first-party lists, and upgrade attribution for agent-driven traffic.

LMSYS Org

@lmsysorg

@AIatMeta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on @NVIDIAAIDev RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been

Avi Flombaum

@aviflombaum

Zuck and @Meta really crushed how amazing @Muse is. I told it about my parking app because I tried using it originally to find parking but it couldn’t do it and like 12 hrs later I got this alert that it could help me