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 ↗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 →The event log: replay-exact, restart-safe
Agents that work for hours need a memory that survives anything. Muse Code’s runtime is built around a single append-only log — and almost every trust property of the product falls out of it.
Read the post →Getting started with Muse Code: from install to first merge
Meta’s terminal coding agent is deliberately minimal to set up: one command, one browser sign-in, and you’re driving a multi-agent session inside your own repository. Here’s the whole path, including the parts worth slowing down for.
Read the post →An autonomous GitHub bot that knows when not to act
The cookbook’s GitHub agent recipe wires triage, PR review, and bug-fix automation into GitHub Actions on OpenCode and Muse Spark. Its most transferable lessons are the guardrails.
Read the post →