Videos

Peter Yang shows 10 real Muse use cases, including having the agent call customer service to lower his cable and phone bills by over $800 a year.

Greg Isenberg explains how a Muse connector works, pitches four startup ideas to build on one, and covers getting customers beyond Meta's directory.

Better Stack runs both new 30B models on autonomous coding, Adobe Premiere control via MCP and parsing a 100+ page SEC filing.

Anil Chandra Naidu Matcha tours what the community-built Muse connector catalog adds to Meta's agent beyond what Meta shipped.

AI Coding Daily re-runs its Muse Spark 1.3 tests using the max reasoning level inside Muse Code.

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.

A harder rematch between Muse Glimmer and Qwen 3.8 27B (bumped to high reasoning) on the TalkWithMe project.

WorldofAI benchmarks Muse Glimmer 30B on consumer hardware with a self-built test harness and compares it against Qwen 3.6 27B.

Fahd Mirza installs Muse Glimmer in GGUF format and tests it with DFlash speculative decoding for faster local inference.

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.

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.

RepoChad examines Muse Spark 1.3's 1,048,576-token context, DeepSWE and TerminalBench results, and the Max vs x-high reasoning modes.

Eric Siu shows the business tasks he gives each agent, including Muse reworking content, and picks a daily driver.

When-Agents-Rule drops Muse Glimmer 30B, Qwen 3.6 27B and Gemma 4 31B on one island to run an economy and fight for 90 minutes with no human input.

Full Value Dan spends a week using Muse to book dinners, sell on Facebook Marketplace, pay bills and triage DMs, scoring it 9/10 as an assistant and 6/10 at precise creative work.

Meta Developers session on what Muse Spark's act-on-perception multimodality unlocks across code, physical action and video workflows, plus Muse Voice Transcribe.

Fahd Mirza puts Muse Spark 1.3 through agentic and coding tasks on launch day.

WEBdoze pairs Muse Spark 1.3 and Gemini 3.8 Flash with the Impeccable design skill and browser testing to turn plain AI-generated pages into polished frontends.

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.

PIMX_ELTEX runs Muse Spark 1.3 in OpenCode on six prompts, from 3D games and an open-world mini GTA to car simulators and web apps, at about 3 minutes per project.

Stream Developers runs Muse Glimmer locally in LM Studio as an always-on coding agent and has it generate a SwiftUI drawing app.

Alex Finn demos Meta's Muse personal agent and walks through what it can do across real tasks.

No place like localhost has Muse Glimmer implement a 7-stage development plan for a classic arcade game clone, the same challenge earlier run against three Qwen models.

Bijan Bowen runs Muse Spark 1.3 through a browser OS, C++ skate game, subway FPS, 3D CAD Hot Wheels, a Blender/Godot wrestling game and more, then tallies the total cost.

Jerrod Lew demos the Meta Muse personal agent at muse.ai and shares an access token so viewers can try it.

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.

Fireship breaks down Meta's Muse Glimmer, a 30B-parameter agentic model released under Apache 2.0, in a short explainer.

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.

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

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

Rich Rose tests Muse on real business tasks for a week: building Excel order forms from color charts, scanning photo order forms, updating pricing and cross-checking out-of-stock items.

Meta Developers session on the Muse Spark and Muse Code build paths: the model provides see/decide/act, the harness provides reliability, scale and auditability for production code.

Digital Spaceport reviews Muse Glimmer 30B on a 4x 3090 EPYC home server, calling it weaker than Qwen 3.6 27B overall but good at one specific thing.

AICodeKing tests Meta's Muse Spark 1.2 and the Muse Code terminal agent on the free tier, covering pricing and features before running KingBench 3.

Softreviewed shows how to get at Muse Spark 1.3 for autonomous, terminal-based coding without paying for a coding subscription.

STARTUP HAKK tests Muse Spark 1.3 and argues the harness, tools and context around a model matter as much as the model, pitching their OpenMonoAgent harness.

Sam Witteveen covers Meta's open-weight Muse Glimmer 30B release, pointing to the research blog and the Hugging Face collection.

Cloud Codes runs Unsloth's 2-bit dynamic quant of Muse Glimmer 30B in about 14 GB of laptop memory and tests 100+ autonomous tool calls.

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.

Theo (t3.gg) tests Meta's Muse Code terminal agent powered by Muse Spark 1.2 and focuses on how cheap it is compared with Claude Code.