Introducing Muse for Marketing
Muse can finally connect to all your ad accounts and SEO tools
Now Muse has access to:
> Google Ads, Meta Ads and 12+ ad platforms
> ChatGPT Ads
> All SEO tools (GSC, GA4, Semrush, Ahrefs)
> Shopify, WordPress, Webflow, HubSpot, PostHog
So Muse
Refusal-direction ablation on Muse-Glimmer-30B that cut refusals from 128/150 to 3/150, adding an agentic-safety evaluation and publishing bf16 and GGUF uncensored weights.
I wanted to try something quick with Muse Spark 1.3, so I had it build this pirate platformer. It was incredibly fast and worked flawlessly at one-shot! Now I’m enhancing the artwork, sprites and adding new levels 😊This is such a fun coding model, it just works, fast and cheap!
MUSE FEATURE ALERT: y'all have been asking for this one. your @muse is getting its own email address. add it to a thread or forward it stuff and it’ll handle it for you.
muse mail!
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)
Muse Code adaptation of Lauren Tan's pstack engineering skills from Cursor: all 45 skills with upstream-verbatim bodies and only the install frontmatter adjusted for Muse.
This is very interesting. I asked Muse to add an interactive map to the page and not only did it do it, but it even wrote and executed its own test script!
Used Muse AI @muse to create and publish my Siri AI Unlocked website. A blog dedicated to Siri AI real world Use Cases, successes & failures. #SiriAI #Siri #ios27 #muse #museai #meta
https://muse.ai/s/siri-ai-unlocked-xzxv5xk9xmhxh7ft
muse spark 1.1 in AdaL Engineer beats Opus4.8 in Claude Code with 20% of the cost
loop engineering, when done right, is beyond just running longer, its delivering better results when contexts are managed well and when workers are better prompted to stay honest.
how GANs had
AgentMail's guide: tell Muse to get an AgentMail address, paste an API key into its Secrets tab, approve the connection and send a test; about five minutes, no code.
Rohan Adwankar found Muse runs on Cloud Hypervisor microVMs with a 327 MB Rust harness that boots in ~40 s, an on-VM Postgres with 194 tables and 60+ privsep tool workers.
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
Meta employee here! I built a finance calculator for Singaporeans to help with adulting decisions, like mortgages, retirement, savings, and a bunch more! Entirely with Muse!
gethowmuch.net
Added @vapiaibusiness + @twilio to @Muse getting incredible results. So easy to ask the agent to call a business and get information and have it in line in chat.
I found a way to spend less time looking at Facebook. My Grok @bot already sends me a morning report with @agentmail , now I gave @Muse its own agentmail and it emails any interesting FB activity from friends to my Grokbot who then adds it to my morning report.
This is a small HTTP API you run on a machine you control. Muse SSHes in and calls http://127.0.0.1:8792. It can search Amazon and add to a personal cart or a Prime Business cart. It does not check out or pay.
https://github.com/aasper03/muse-amazon-bypass
You need Python 3.11 and curl. Sign in to Amazon in a normal browser and export cookies for each account. Amazon blocks automated login windows. The README covers Muse-over-SSH setup, and a later section shows how to call the same API yourself.
A Claude Code plugin that adds /muse:review, /muse:critique, /muse:delegate and /muse:transfer commands, running Muse Code reviews and delegated tasks as background jobs.
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.
Its been 1 day and I had added almost 100 features to 4 apps im building while I slept
300m tokens used
Muse QA’s them and pushed to prod as well
If you want 1B tokens free sign up here
Redeem my code in Settings within 48 hours of joining and we'll both get 1 billion @Muse
Muse Spark 1.1 has entered the Code Arena: Frontend at #9!
Muse Spark 1.1 reshapes the cost-performance Pareto Frontier by scoring 1541 at a blended $3.5M ($1.25 per input MToken, $4.25 per output MToken). This is frontier performance at a fraction of the price.
Congrats to
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.
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.
Demo of a QLoRA adapter for Muse Glimmer 30B that points at UI elements in web screenshots, returning a click point from an instruction like "filter by MATEIN brand".
Packaging for Meta's Muse Code on Arch Linux (AUR) and Android Termux ARM64, adding AVX2 emulation for older CPUs, a TUI session manager and multi-agent MCP sync.
Been playing around with @Muse this morning 🤯
Got my agent, Satoshi, setup with a bitcoin balance using @Breez_Tech
Received some sats, moved some sats. Fun!
📩 muse@breez.tips h
1/ we’ve built a lot of connectors to make it easier to integrate Muse into your life. Muse runs in a secure VM and we don’t use your data for ads or anything other than to make Muse great for you. you can connect Muse to Gmail, Google calendar, Outlook, Plaid, Opentable, Google
Today @muse:
-booked and paid for airport parking, after recommending the best location for charging a @Tesla
-advised on flights for an upcoming trip during my kids’ fall break timeframe (which it found)
-read a receipt from @AceHardware and found that the prices were better
Pi coding agent extension that adds Muse Spark 1.2, 1.2-contributor and 1.1 via the Meta Model API, a maintained fork that fixes a false auth warning on pi v0.84+.
AgentMail's Muse page gives the agent its own email address so it can send, receive and sign up for services as itself while the user's Gmail stays separate.
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.
A reproducible RDNA reference that adapts MI-series ROCm recipes to run Muse-Glimmer-30B on Ryzen AI (Radeon 8060S) hardware, measuring 2.2–2.5x single-stream speedups from DFlash.
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.
Peloton is a launch connector for Muse, Meta's new personal AI agent app, which can search the class library, add to your schedule, build full training plans, monitor the Peloton schedule for new classes and alert you, & more. $PTON #Peloton #OnePeloton pelobuddy.com/muse-peloton-f…
musecode adds a /musecode slash command, a Haiku relay agent and a muse-run CLI so Claude Code Workflow fan-outs run their leaf tasks on the free Muse Spark 1.3 model through opencode.
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
Ported a Miniature Golf prototype to VR using Meta Muse Code and the Unity CLI, added dozens of automated tests, and built a website to capture test runs, screenshots and results.
PyTorch added end-to-end Muse Glimmer support to ExecuTorch; on an M5 Pro, DFlash speculative decoding lifts image+text decode from 21.6 to 33.0 tok/s, and it powers the Pi coding agent locally.
Been tinkering with speculative decoding on Apple Silicon for a while, and this week I got Meta's new Muse Glimmer 30B working in my project mlx-dspark. On my M4 Pro, the 8-bit model goes from 8.2 tok/s to 18-26 tok/s depending on content. Math is the best case at 3.27x, code 2.5x, chat 2.22x. Output is byte-identical to normal decoding since the target verifies every token, so there's no quality tradeoff; it's just faster.
Meta's own DFlash numbers on Mac are 1.5x (M4 Max) / 1.8x (M5 Max), but those are on the 4-bit build, so not really apples-to-apples. 4-bit for me is ~1.7x at ~25 tok/s and only needs ~18GB. The 8-bit run peaks around 40GB, so you want a 48GB Mac for it. Basically, you get 8-bit quality at 4-bit speed.
Repo: github.com/ARahim3/mlx-dspark
I'm happy to hear feedback, and I'm curious about what other M-series chips get.
Motion Labs shows how to connect a product catalog to Advantage+ Catalog Ads and the Meta Model API with Muse Spark 1.1, plus compliance checks for agencies.
holy shit, @Muse just caught $1,742 a week leaking out of my ad account
I asked one question about my ad spend. It did everything else by itself:
> Pulled Meta, my pixel and GA4 and noticed the numbers didn't match
> Split it by age, device and creative, found 4 dead ads eating
Emailed the doctor's office, left a voicemail, filled the new-patient paperwork, got the confirmation back, added it to the calendar — ~5 minutes. @muse does the admin you'd have postponed for a month
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.
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.
✨ Three New Models, Sharper Lore Awareness & Smoother Storytelling Across Complex Worlds
This update introduces three new storytelling models, improves how Lore is recognized and prioritized during a story, and brings another round of reliability improvements to the model experience.
🎭 Three New Voices 💎 Gemini 3.8 Flash — Pro+ Google’s newest fast storyteller, with polished prose, responsive pacing, and a steady grip on complex scenes.
Context support:
🔹 16K on Pro
🔹 48K on Ultra
🔹 80K on Legendary
Context limits subject to change.
✨ Muse Spark 1.3 — Plus+ Vivid character interplay, strong world-state awareness, and deliberate continuity as stories evolve.
Context support:
🔹 16K on Plus
🔹 32K on Pro
🔹 64K on Ultra
🔹 100K on Legendary
🌐 Hunyuan 4 Preview — Pro+ Built for ambitious living worlds, shifting relationships, and large casts with lasting consequences.
Context support:
🔹 16K on Pro
🔹 32K on Ultra
🔹 48K on Legendary
📚 Sharper Lore Awareness Lore is getting better at recognizing what matters in the current scene.
🏷️ Smarter Lore activation — Lore cards can now activate when their title or character name appears naturally in the story, even
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.
Muse Spark 1.3 released today, so I immediately tried it in Muse Code with the Miniature Golf game I previously converted to VR using version 1.2!
💻 The prompt “Add Hands support & allow for hands or controllers. Use MetaVR CLI for additional ISDK context”
The entire process
You can now run Muse Code (and Muse Spark 1.3) in cloud agents on @tryreplicas!
Bring your own Muse subscription - they're surprisingly generous and powerful.
Muse Code plugin that finds friends' birthdays across Instagram, Facebook, Messenger and WhatsApp and adds them to Google Calendar as yearly events, with approval.
An OpenCode plugin that ports Muse Code's subagent coordination core: durable child workers, a ledger mailbox and admission control, so subagents survive crashes and respect capacity.
Muse Spark 1.2 (xHigh) by @AIatMeta is now in Agent Arena, with a net improvement of +2.1%!
Agent Arena measures models on millions of real-world, long-horizon agentic tasks. We use causal tracing methodology to measure a model's net improvement, indicating how much it improves
Muse Code OpenRouter is a small local adapter that lets the Muse Code harness run any meta/muse* model through an OpenRouter key instead of a Meta login.
Muse Glimmer is now available to run with Ollama.
Available today via Ollama’s MLX engine with state-of-the-art-performance on Apple Silicon, Muse Glimmer can power Claude Code, Codex, and more always-on local agent workflows natively using Ollama.
Additional support and
Maestro is a suite of native Muse Code plugins adding a command guardrail, proof-of-done checks, session-size watch, secret redaction, persistent memory and token/cost telemetry.
An architecture port adding the muse_glimmer model class (vision tower, language model, projector and image processor) to mlx-vlm, so any Muse Glimmer checkpoint runs multimodally on Apple Silicon.
We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container.
So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added
Adversarial-review and fix-verification skills for Muse, built after two round-1 reviewers approved a diff with 0 blocking findings while an independent review found 13 real issues.
A five-minute setup that gives Muse its own Dead Simple Email inbox through a custom connector, so it can handle email-verified signups away from your personal Gmail.
An effort to make Muse Glimmer 30B actually use a 512k-token context (4x native) as a ~17GB GGUF in 32GB VRAM, trained on DGX Spark and evaluated with RULER-style retrieval tests.
PostFast's sourced catalog of every known Muse connector: launch partners, Meta's own connectors, post-launch additions like Notion, Granola, Spotify and Railway, and announced-but-not-live ones.
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.
Finally put @Muse to the test. Pretty shocked. I had it find unclaimed property and file all the paperwork. Free $97. Then I had it opt me out to all major data brokers. Finally, I had it add all my Amex offers. Saved 200 manual clicks. @alexandr_wang 🫡
The Spotify connector in Muse feels like the start of Cursor for music and podcasts.
It can find create playlists for content you’re interested in and update your playlists everyday on a recurrent basis. It can also generate brand new podcasts and add those podcasts to a