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 ↗Muse Code API key: how to create one, use it in CI, and what it costs
Muse Code can sign in with a browser or an API key, and the key is also your way into Meta’s Model API. How to create a key, the environment variable each tool expects (META_API_KEY vs. MODEL_API_KEY), base URLs, per-token prices, rate limits, and the mistakes that cause surprise bills.
Read the post →Muse Code CLI cheat sheet: commands, flags, and shortcuts
Every Muse Code command worth knowing on one page: install and sign-in, slash commands, keyboard shortcuts, muse exec for CI, approval modes and --yolo, models and reasoning effort, skills, MCP, and where the config lives.
Read the post →Muse Code vs. Claude Code: price, benchmarks, and which one to use
Claude Code still edges Meta’s agent on most coding benchmarks, but Muse Code starts at $5 a month and its fastest runs finish in half the time. A side-by-side of plans, API prices, independent scores, privacy defaults, and how to switch between them.
Read the post →Muse Code vs. Codex: Meta’s and OpenAI’s coding agents compared
Muse Code edges OpenAI’s Codex on independent coding-agent benchmarks, but Codex comes bundled with ChatGPT and runs in far more places. Plans, prices, scores, speed, open-source status, and where Cursor fits in.
Read the post →What’s new in Muse Code 1.4: native Windows, /model, skills import, and more
The Muse Code CLI 1.4 series brought a native Windows installer, direct model switching, Claude and Codex skill import, image and video features, and quieter fixes to Contributor mode and the sandbox. Here’s what changed, grouped by what you’ll actually use.
Read the post →Muse Spark Open: can you run Meta’s open-weight model, and Muse Code, locally?
Meta released Muse Spark Open on October 15: 816B parameters, a custom license, and a hardware bill most developers can’t meet. Here’s what the license allows, what it takes to run, and what Meta has and hasn’t said about running Muse Code on it.
Read the post →Muse Wonder and Wonder Full in Muse Code: plans, prices, and the launch-day bug
Meta’s first frontier models arrived on October 12 with a new $200 Maximum plan. Here’s which Muse Code plan gets Wonder or Wonder Full, what Wonder costs on the API next to Spark 1.3, and whether an upgrade is worth it.
Read the post →Muse Code download and install guide: macOS, Linux, and Windows
There is no Muse Code desktop app to download — every platform installs with one terminal command, including a native PowerShell installer for Windows. How to install it on a Mac, Linux, or Windows (natively or through WSL2), keep it updated, fix common install errors, and uninstall it.
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 plans from $5 to $200. Both have tiers called Power and Maximum. 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 →