News & deep dives.
Announcements, research notes, and practical guides on Muse Code, Muse Spark, and the Meta Model API.
Introducing Muse Code and Muse Spark 1.2
A terminal coding agent powered by our newest model — persistent background agents, repository-scale execution, and built-in verification. This marks the next step toward the frontier, with larger and much more capable models on the way.
Read on Meta AI Research ↗How to install Muse Code on macOS, Linux, and Windows (WSL2)
There is no Muse Code desktop app and no Windows installer — just a one-line terminal install. Here’s how to get it running on a Mac, on Linux, and on Windows through WSL2, plus what to do about VS Code.
Read the post →Meta Muse vs. Muse Code: which subscription do you actually need?
Meta now sells two things called Muse: a consumer agent with $20 and $100 plans, and a coding agent with $5, $15, and $50 plans. Both have a tier called Power. Here’s how to tell them apart before you pay.
Read the post →Muse Spark 1.3: what changed, what it costs, and where to use it
Meta’s September model update replaced Muse Spark 1.2 inside Muse Code without raising prices. The headline benchmarks come with a caveat — and the efficiency gains may matter more to your bill.
Read the post →Meta enters the agent race: the business story behind Muse Code
Strip away the benchmarks and Muse Code is a strategic statement: Meta’s first coding agent, priced to undercut the incumbents, shipped by the lab Alexandr Wang was hired to run.
Read the post →Muse Code vs. the field: the price-capability map
Five serious rivals, two axes that matter. Where Meta’s agent actually sits against Claude, Codex, DeepSeek, GLM, and MiniMax — and a decision framework that survives the next price change.
Read the post →Agent fan-out and git worktrees: parallel edits without collisions
Parallelism is easy to promise and hard to make safe. Muse Code’s answer is old, boring git technology used exactly right.
Read the post →Why Muse Code keeps its agents alive all session
The quiet architectural decision behind Muse Code’s speed: background agents that persist for the whole session instead of being spawned per task and thrown away.
Read the post →/plan, /grill, /goal: the built-in skills workflow
Meta’s one-line pitch for Muse Code’s bundled skills: put a rough idea in, get a grilled, taste-checked feature out. Here’s what each command actually does and when to reach for it.
Read the post →Contributor vs. Standard: doing the tier math
The two ways to pay for Muse Spark 1.2 differ by more than an order of magnitude. The right choice isn’t one tier — it’s a per-project policy.
Read the post →28 recipes, three sections: a field guide to the Model API cookbook
Meta’s cookbook promises recipes that run the first time you copy them. The promise holds because of how it’s structured — each section assumes exactly what the previous one proved.
Read the post →