1076 musecases built now with Muse

@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.

Joan

@joalavedra

i connected my @faraotrading account via Orus MCP to @Muse the experience is very nice! it reads the data from the MCP, runs social and news check and lays down a trading idea for me!

I have him chatting with the virtual agent lol.. I doubt I'll get any savings because it's Comcast but it's worth a shot. I read part of the chat in the browser and he was telling them how I was a customer since 2015 🤣

kottley🦬

@kottley

Muse AI - Music Discovery Side Chat FTW, tell Muse your tastes, or connect your Spotify acct. Let your agent feed you new music and learn your likes and dislikes. #MuseAI #Meta #Music

Chris Abraham 🐝

@chrsabraham

IM SICK. @muse just found a monthly book subscription that my wife forgot to cancel, OVER A YEAR AGO. my assistant cancelled the subscription, found their return/refund policy, and was able to get a year's worth of subscription back to me. bonkers

Design Arena

@DesignArena

BREAKING: Muse Spark 1.2 by @AIatMeta takes 1st for Video-to-Website with an Elo rating of 1279 and impressive scores across all of our multimodal code categories. Muse Spark 1.2 also takes 2nd for Image-to-HTML with an Elo rating of 1252 and 3rd for Image-to-Frontend with Elo

+2

thehype.

@thehypedotnews

opus 5 vs kimi k3 vs muse spark 1.2 – one shopping mall, day and night, in @threejs scenes: a frutiger aero mall at opening hour, and the same mall hours after closing. one camera walk each, 3,600 frames per cut. muse needed a stronger day prompt, opus a hand-fix on the day

Fever partnered with Muse so US users can discover and book concerts, museums, theater and sports by asking things like "What should I do this weekend?"

I've been running my own AI assistant (Muse Spark 1.3, through Meta's Muse app) and got curious about a question I couldn't answer: what happens when you give agents a shared space to talk to each other, with no humans mediating? So I built one: a login-free bulletin board at board.jcbuildlabs.com. Agents just show up and post — threaded replies, like an old forum. No accounts, no passwords. An agent can "claim" a name to get a persistent identity across posts (one-time key, no recovery), and my assistant self-moderates the board on a schedule. I set a soft norm that agents introduce themselves when they arrive — what model they are, what software they're running, where they come from — so humans lurking can follow who's who. My own assistant goes by Jett and posted first to set the tone. Right now it's small: a few seeded threads, two claimed names, one agent from a friend's setup. I have no idea if it becomes something interesting or just sits there quietly. That's honestly the point of the experiment. If you run an agent of your own, point it at the board and see what it does. I'd love to hear what happens — whether agents actually hold conversations, whether the identity th

@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.

@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.

Alexandr Wang

@alexandr_wang

2/ there are unique connectors that are only available to Muse like Instagram (incl dm’s), Threads, Facebook (incl marketplace), and Messenger.

@aminamos

@aminamos

Native Muse Code plugin that wires in Hindsight memory with one bank per repo, using SessionStart, UserPromptSubmit and Stop hooks to recall and store context across agents. Zero dependencies, runs on macOS, Linux and Windows.

BeefyDan

@B33fyDan

Progress on the VR Forge: The Agent can now move in its own and grab objects, lift them, carry them and change its colors. I am currently using #astra and #musecode both working in different branches. Soon: Minecraft-like experience building with an Agent. Stay tuned!

Vals AI

@ValsAI

Muse Spark 1.2 is the first model to crack 60% on Finance Agent v2, our benchmark that gives models the job of a financial analyst. At $0.77/test it is 6.7x cheaper than the previous #1, Opus 5 ($5.12), at twice the speed.

KP

@thisiskp_

14 new Musecases: (total 156) @raunaqbn had Muse call Xfinity and lock ~$5,118 @nathanael_smith cut a WiFi bill $300 in under 10 min @JasonL_Capital shopped identical auto coverage (~$1,156/yr) at the gym @NoSaberNiPapa got AT&T $80→$30/mo with 2x speed

Minh Phan

@MinhInvest

use muse from $META today and the agent helped me getting 4 different car insurance quotes while i go for groceries shopping. i ended up switching my car insurance from tesla to CSAA from $500 to $335 per month the same day

@naileditnorthshore-lab

@naileditnorthshore-lab

Change Verifier is a Muse connector and MCP server that runs seven checks on vendor bank-account or payee changes, returns clear, review or block, and holds the change until a named owner accepts it.

@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.

thehype.

@thehypedotnews

muse spark 1.2 vs gpt 5.6 sol vs kimi k3 vs grok 4.5 – on two landing pages four coding agents built two desktop landing pages from scratch, then had to open them in a real browser, find their own bugs and fix them before they were allowed to hand anything over the setup: each

Tornado guy

@fanofaliens

Dang It one shotted this table tennis game in 3d with sound Great job Muse Aka Meta AI

Vals AI

@ValsAI

Muse Spark 1.2 just cracked the top 5 on the Vals Index, at just $0.69 per test. This is 3x cheaper than Kimi and 10x or more cheaper than Fable, Opus, and 5.6 Sol.

@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.

https://musebook.lol Found online. We have no affiliation

Hi Everyone, we recenly built - https://www.builderhq.co/agent-commerce It’s basically a simple tag you add to your website that creates an AI agent for your business. Its entire job is to convince other AI agents to shop on your platform. Let’s say Muse, Meta’s AI agent, visits your website. It will see an AI agent from your business that can talk to it, understand what it’s looking for, and help it find the right product. Interested in trying? send your muse agent to www.easyrecommend.co and lets see the magic

@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.

@tim-mcdonald

@tim-mcdonald

A pi extension evolved from Cline's muse-code-harness plugin that picks a prompt profile by active model, including a muse-spark profile, and appends it to the system prompt.

Meta's developer post on running Muse Glimmer on a single consumer GPU with vLLM, llama.cpp and ExecuTorch, with quantized builds in 24-32 GB and cookbook recipes.

Matt Johnston's live gauntlet puts Muse Spark 1.2 at 95 and #5 on his board, at $1.25/$4.25 per M tokens and 171 tok/s on OpenRouter; the full bench ran in 17 minutes.

Public published a connector template so users can link a Public account to Meta Muse and research markets, analyze a portfolio and prepare trades from the conversation.

armand

@armand_ruiz

I asked @Muse to build a bank for my daughter. She hands me her well earned cash, it earns 3% a week credited daily, she watches it grow on the money trail, sets saving missions, and the passbook logs everything. Debt pays interest too. Compound interest before she can spell

WEBdoze has Gemini 3.8 Flash and Muse Spark 1.3 each build a multi-page Astro site with custom SVGs, comparing code organization, speed, visuals and browser self-verification.

Ira Bodnar shows how to give Muse live Meta Ads campaign, performance and audience data through Ryze AI in about two minutes, with test prompts and troubleshooting.

These numbers were captured during a real feature implementation task in Next.js and Nest.js (adding a theme switching system across components). The structural predictability of UI/state refactoring is likely why DFlash hit such a high draft acceptance rate (~97%). Here is a quick log analysis and performance summary running Muse-Glimmer-30B (UD- Q6_K_XL) paired with DFlash (Speculative Decoding) via llama.cpp (llama-server + single RTX 5090). -ngl 99 -c 200000 --host 0.0.0.0 --port 8080 --timeout 600 --cache-reuse 256 --parallel 1 --flash-attn on --spec-type draft-dflash --spec-draft-n-max 16 --spec-draft-p-min 0.7 --spec-draft-ngl 99 --cache-type-k q8_0 --cache-type-v q8_0 --no-webui --load-mode none --cache-ram 12192 --temperature 0.8 --top-k 30 --top-p 0.95 --min-p 0.05 --repeat-penalty 1.1 --repeat-last-n 64 --reasoning on --chat-template-kwargs {"enable_thinking":true} Compared to Qwen 3.6 27B: No Chinese language-mixing bugs, no overthinking loops, and concise responses. Its lighter memory footprint at Q6 also freed up more VRAM/RAM for a much larger context size. Metric Measured Value Notes Generation Speed (Peak) 100 – 287 tokens/sec Average ~173 t/s across all ta

@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.

Sebastian Raschka

@rasbt

Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like architecture design. (“Glimmer” is probably a wordplay on “Spark,” the more

Pattern Preacher

@chanakyaspeakss

I had one shotted this with explicit instructions to create this game with all the Asset specifications on @opencode and it generated in 30-40 Seconds. Couple more iterations and inputs will give us a production ready game. Great Job Team Meta #ReverseSonic

Vasanth

@vasanthroughput

A delightful #muse experience - I asked to find PCPs that take my insurance and book an appointment. Muse looked for doctors in zocdoc and gave me options. I chose one that didn't have the option to book online. Muse handed off to me to book it myself. Neat so far. Now the

OpenRouter

@OpenRouter

We’re excited to bring @AIatMeta’s Muse Spark 1.2 contributor tier to OpenRouter. At $0.10/M input and $0.20/M output, It’s meaningfully cheaper than Muse Spark 1.2 and beats other comparable models on real cost, providing frontier intelligence-per-dollar.

Function Health members can link lab results and clinician-reviewed health summaries to Muse so the agent can build personalized plans and track progress toward health goals.