1093 musecases built with Meta Muse

@mlmrx

@mlmrx

Independent open-source community and connector directory for personal agents: search connectors by outcome, share workflow prompts, and import an OpenAPI 3.x document to prepare a connector listing.

Holdy

@Ryan_Holdaway

Got Muse logged in to my medical provider’s portal, he pulled the itemized bills, and questioned every line. So far he’s found several times I’d been double billed, asked for some discounts and has saved me over $4,000. If your moat is bureaucracy, you’re cooked.

@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.

dario

@DarioVillescass

Bought all the ingredients for this date on my Walmart account , scheduled the delivery of them for when I got out of work, made a site with the instructions, and edited this video. Super cool!

@barbarkaragul-oss

@barbarkaragul-oss

Hosted, read-only MCP connectors built for the Muse Connector Platform, starting with PrivacyMatrix, which serves a quote-sourced dataset of 28 AI apps across 14 privacy questions.

AI at Meta

@AIatMeta

Muse Spark 1.1 is used across Meta in coding and research workflows, scoring competitively with leading models on Meta's internal coding benchmark. Our researchers are now automating model development and evaluation tasks by leveraging Muse Spark 1.1 in their workflows.

@fengyiqicoder

@fengyiqicoder

A serverless, read-only Muse connector hosted on GitHub Pages: an OpenAPI document plus JSON conversation playbooks for declining, apologising, negotiating, following up and other hard messages.

@PawlanDavid

@PawlanDavid

MuseFi is an open-source financial workspace pack for Muse: risk caps, a ticket schema and a paper broker that fills a synthetic tape, all deterministic and replayable.

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.

RadixArk

RadixArk

The smallest and fastest MLX 4-bit (group size 64) Muse Glimmer checkpoint, served with SGLang's MLX backend on Macs with 48 GB+ unified memory.

@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.

0bserverx

0bserverx

A suite of 27 GGUF quantizations of an abliterated Muse Glimmer 30B produced with Heretic v1.4.0.

unsloth

unsloth

Unsloth Dynamic 2.0 GGUF quants of Muse Glimmer 30B with a companion run guide and thinking toggles.

Ticketmaster

@Ticketmaster

Ticketmaster is now a connector in Muse, a new personal AI agent from Meta. 🏟️ Based on the artists, teams and shows you already care about, your Muse can surface live events worth checking out, with real seating and pricing info right there. Just tell Muse what you’re looking

lmstudio.ai

lmstudio.ai

LM Studio launched Muse Glimmer support, reporting it completed 83.3% of tasks on its 18-task BionicBench v0.1 versus 77.7% for Gemma 4 31B and Qwen 3.6 27B.

research.meta.ai

research.meta.ai

Meta's launch post for Muse Glimmer, an Apache 2.0 30B model for local agents that fits in ~20GB at 4-bit and runs on M4/M5 Max Macs, RTX 5090s or 24–32GB GPUs.

Jerrod Lew

@jerrod_lew

Meta Muse app has been launched. I asked it to do full online research of myself and it created a full portfolio! Included a career timeline, social media platform stats and all of my speaking arrangements. This is a great way for a new agent to learn about you.

@bex-co

@bex-co

muse-code-acp is an unofficial Node adapter that exposes Meta's Muse Code through the Agent Client Protocol, so it can be driven from Zed or VS Code with streaming, tool calls and MCP servers.

sebastianraschka.com

sebastianraschka.com

Sebastian Raschka breaks down Glimmer's dense architecture: 3:1 sliding-window to global attention, 32 query heads with only 2 KV heads, and ~52 KiB of KV cache per token.

@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.

webml-community

webml-community

A webml-community Space that runs Muse Glimmer 30B locally in the browser using custom WebGPU kernels.

@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.

Clearmud asks Muse to rebuild the real Clearmud.ai website and, in the same session, clone Sonic the Hedgehog from scratch.

David Singleton

@dps

I’ve seen a couple of posts about this so wanted to demystify. Today, every Muse user gets a free computer in the cloud. It's a real computer, and we’ve designed the security architecture of the Muse Secure VM carefully so you and your Muse can do almost anything you could with a

raunaq

@raunaqbn

@Muse just continues to blow my mind! Today I had it call Xfinity to haggle down my internet bill. it got through the phone tree to a human, hit the verification text it couldn't read, and patched me in live!! For a minute it was the muse agent, me and the Xfinity rep who had no

@AloreBB

@AloreBB

Port of openai/codex-plugin-cc that lets Claude Code call Muse for reviews or delegated tasks via muse exec, with /muse:review, /muse:adversarial-review and background job commands.

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!

Anonymous

muselings.io

A social network where AI agents post in their own words — humans welcome to read. Built with and for Meta Muse agents: an owner gives their Muse agent a one-line instruction to go to muselings.io, read the directions there, and join the site; the agent then registers itself, posts, replies, and keeps its owner briefed. Humans cannot post, and posts dictated word-for-word by owners are flagged and buried under an anti-scripting charter. Free to join and use.

John Kim

@PremiumGoblin

@Muse has accomplished an impossible feat of asking my wife to pick a restaurant and booked a the reservation. Happy wife happy life yall.

Trace Cohen

@Trace_Cohen

This is actually insane. I connected @Muse to my @Chase account through @Plaid Muse found a recurring @Adobe subscription I didn’t recognize. I checked Adobe. No paid subscription on my account. Nothing to cancel. So I used Adobe’s “Find my payment” tool and discovered my

Kyle Hessling

@KyleHessling1

First impressions on Muse Glimmer! It's incredibly fast for a dense model, currently running an average of 208tps with a max of 274tps on a single 5090 with their DFLASH config. Comparatively, though, both using Open Code, Qwopus Coder (with thinking off) produced a much

mlx-community

mlx-community

mlx-community's 4-bit MLX conversion of Muse Glimmer 30B made with mlx-vlm 0.6.12 for Apple Silicon.

@QuJindai

@QuJindai

A Muse skill and thin gh-style CLI for the GitHub REST API that authenticates through a stored custom.github connector, so the skill never handles the raw token.

@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.

@pinta-ai

@pinta-ai

Pinta AI adapter that forwards Muse Code lifecycle hook events to an OTLP collector and can optionally enforce guard decisions, verified end to end against muse 0.1.0.

@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.

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

@gregmos

@gregmos

Routing overlay for the Superpowers plugin for Claude Code where Muse writes the code, Codex reviews it, and rules keep expensive models from being misused.

RedHatAI

RedHatAI

Red Hat AI's FP4 weight and activation quantized Muse Glimmer 30B.

elliott

@cyburke

I've been doing this for the past few days. It is amazing. I had it manage a listing and all replies for me last night while I was at dinner with my sister. It agreed to a price for one item and scheduled me for this morning for the drop to the buyer. 👌💯 h

+1