Independent reference

What Is Muse Code? Meta's Coding Agent, Explained

Muse Code is Meta's terminal coding agent, released in beta on 5 August 2026 by Meta Superintelligence Labs and driven by Muse Spark 1.2. What is Muse Code offering that other CLI agents are not? Persistent background agents, a replayable event log, and per-token billing with no subscription.

Product
Muse Code (beta), terminal agent from Meta Superintelligence Labs
Released
5 August 2026
Model
Muse Spark 1.2, co-trained with Muse Code
Context
1M tokens; image, video and PDF input
Platforms
macOS and Linux only; no native Windows build
Command
muse, installed to ~/.local/bin
Named skills
/plan, /grill, /goal
Billing
Per token; no monthly plan, no free quota

What Is Muse Code? The 30-Second Definition

What is Muse Code in one paragraph, plus the search names it answers to.

Muse Code is a coding agent living in your terminal. You run muse from a repository, describe a task, and Muse Code reads files, edits them, runs commands and iterates. No IDE, no browser app, no desktop client.

One product answers to many search names: Muse Code meta, meta code, meta ai code, meta coding agent, meta coding ai, meta ai coding agent and meta terminal coding agent all point at this binary. Muse Code beta is its release state.

One disambiguation: Meta Spark was Meta's retired augmented-reality platform, unrelated to Muse Spark 1.2 or Muse Code. Adobe Muse and MuseScore share four letters, nothing more.

What Is Muse Code Made Of? Agent Loop, Background Agents, Event Log

What is Muse Code architecturally: a tool-calling loop, resident background agents, a local log.

Agent loop

At base sits a familiar loop: Muse Spark 1.2 gets your instruction plus repository context, picks a tool call, and results feed back. What differs is stamina — Meta AI Research reports Muse Code runs exceeding 1,000 tool calls.

Persistent asynchronous background agents

Muse Code background agents are asynchronous and stay alive for a whole session instead of respawning per sub-task. An agent that mapped your build system keeps that understanding — no re-reading the same files every turn.

Append-only event log

Every step is appended to a local event log. Ordered and never rewritten, it lets a session replay exactly and a killed session restart from its last event — replay-exact and restart-safe are Meta's words. On the Hacker News launch thread, crash recovery was among few features commenters called interesting.

Worktree parallelism

Muse Code fans work across git worktrees so changes proceed at once without colliding. That log sits on your own disk — privacy consequences on the Muse Code privacy page.

What Is Muse Code Bundled With? /plan, /grill and /goal

Meta names three default Muse Code skills and publishes no total for what else ships in the box.

/plan — a plan you approve

/plan turns a request into an explicit plan and waits for approval before Muse Code touches files — the gate between describing a task and editing code.

/grill — stress-test the plan

/grill attacks a plan: unstated assumptions, missing edge cases, steps that will not survive your codebase. Cheapest way to stop Muse Code building the wrong thing.

/goal — drive toward an outcome

/goal points Muse Code at a target state and lets it work across many steps — the skill behind Meta's long-horizon runs.

How many skills ship?

Meta writes that Muse Code includes "several default skills" and names only these three. Community reports suggest around ten, including a taste skill, but that is unconfirmed — weighed on our skills and plugins page.

What Is Muse Code Able to Build? Two Official Demos

What is Muse Code demonstrably good at: a multimodal website build and a 24-hour GPU kernel run.

Video in, website out

Meta's multimodal demo travelled furthest: a user drops an mp4 fly-through video of a house into a terminal, and Muse Code produces a marketing and booking page for it — video in, handled natively rather than transcribed.

Long-horizon GPU kernel case

Meta's second showcase runs on NVIDIA Hopper hardware: Muse Code optimised GPU kernels against an FLA Triton KDA baseline, making 1,000+ tool calls over sessions up to 24 hours long. Meta describes substantial improvements but publishes no speedup figure, so treat it as Meta-reported; a Hacker News commenter noted Muse lost to GPT-5.6 Sol there.

Both demos point one way: Muse Code targets tasks measured in hours, not autocomplete. For duller failures, see our troubleshooting guide.

What Is Muse Code Running On? The Muse Spark 1.2 Model

One paragraph on the model, because Muse Spark 1.2 specs and benchmarks have their own page.

Muse Code runs on Muse Spark 1.2, Meta's own model, released the same day and co-trained with Muse Code: 1M-token context, image, video and PDF input, roughly 165 tokens per second in Artificial Analysis testing, which scores it 54 on its Intelligence Index against 51 for Muse Spark 1.1. Parameter count and knowledge cutoff are unpublished. Specs, labelled Meta-reported benchmarks and open weights live on the Muse Spark 1.2 page; see also our Muse Spark API guide.

What Is Muse Code Supported On? Platforms and Install

Muse Code supports macOS and Linux only, installs with one command, and signs in through Meta OAuth.

Its launcher hard-codes four targets — arm64 and x86, macOS and Linux — so Muse Code runs nowhere else natively. One command from Meta's install script places a muse binary in ~/.local/bin:

curl -fsSL https://dev.meta.ai/install.sh | bash

Sign-in is a device-style OAuth flow through auth.meta.com: Muse Code prints a verification link and polls until you approve. That is why it fails inside Docker containers, which lack a browser and a usable /dev/tty.

Windows has no native build; WSL2 is the working route, and Meta has said nothing about supporting it — see our Windows guide. Setup sits on the Muse Code install guide.

What Is Muse Code Priced At? Tokens Only, No Subscription

What is Muse Code costing you? Two per-token tiers, no monthly plan, and no advertised free allowance.

Muse Code has no subscription: attach a payment method and pay per token across two tiers. Standard is $1.25 per million input and $4.25 per million output; Contributor is $0.10 and $0.20 — roughly twenty times cheaper if you let Meta train on your prompts. All as reported, checked against Meta's pricing and rate limits docs. There is no hard spending cap, only email alerts — early users' loudest complaint. Detail sits on the Muse Code pricing page and our cost calculator.

Muse Code vs Claude Code, Codex and Cursor

What is Muse Code worth choosing over? Here it sits beside the three agents it meets most.

Muse CodeClaude CodeOpenAI CodexCursor
Form factorTerminal onlyTerminal + desktop appCLI, IDE and cloudAI IDE
ModelMuse Spark 1.2Opus 5 / Sonnet 5GPT-5.6 Sol / TerraComposer 2.x + frontier
Entry pricePer token, no planPro $17–20/moGo $8 / Plus $20Pro $20/mo
Native WindowsNoYesUnverifiedYes
Free tierNone advertisedNoneYesYes (Hobby)
Standout1M context, cheap tokens, video inputCross-platform, MCP, enterprise controlsCloud async tasksIDE-native agent

Competitor prices as reported, August 2026. Head to head: Muse Code vs Claude Code, Muse Code vs Codex, Muse Code vs Cursor, Muse Code vs GitHub Copilot.

Where to Go Next With Muse Code

Where each thread in this what is Muse Code overview continues in depth.

Frequently Asked Questions

How does Muse Code rank compared to Claude Code?

Behind on benchmarks, ahead on price. Artificial Analysis measures Muse Spark 1.2 at 80% on Terminal-Bench v2.1, and Meta's own reported 82.9% still trails Claude Opus 5 at 86.7%, as relayed by press. What is Muse Code winning on? Token cost and context length — see our full comparison.

Is Muse Code open source?

No. Neither Muse Code itself nor Muse Spark 1.2 weights are released. The agent ships as a prebuilt binary, and the model is served only through Meta's API and resellers. Asked about open weights, Mark Zuckerberg said he would have more to share soon, as reported by The Register.

Why is a social media company offering a coding agent?

Because a frontier model needs distribution and an agent generates training-grade data. Muse Spark 1.2 was co-trained with Muse Code, making it both product and proving ground for Meta Superintelligence Labs. Contributor pricing states the second motive plainly: a roughly twentyfold discount for training rights.

Is Muse Code built on Codex CLI?

Unconfirmed, and nobody has shown proof. The rumour spread because parts of the CLI feel familiar, but Muse Code ships as a compiled binary with no published source, so nobody outside Meta has demonstrated shared lineage. Meta has not addressed the question, so treat it as speculation.

Is there a Muse Code IDE extension or Mac app?

Not in beta. Muse Code is terminal-only: no VS Code extension, no JetBrains plugin, no desktop app. Meta has made no public statement about IDE integration, so any timeline you read elsewhere is a guess. If IDE-native agents appeal more, our Cursor comparison covers that difference.

Is Muse Code free to try?

There is no advertised free tier. Billing runs per token from your first call, and a payment method is required. Community reports suggest a $20 starter credit existed during the Muse Spark 1.1 era, but whether it still applies is unverified. Read our pricing breakdown first.

What is Muse Code beta still missing?

Four gaps stand out: native Windows, any IDE surface, a hard spending cap, and documentation for skills beyond /plan, /grill and /goal. Sign-in also fails inside Docker containers, because that OAuth flow needs a browser. So what is Muse Code today? A one-day-old beta with obvious edges.

Sources

  1. Meta AI Research — Introducing Muse Code and Muse Spark 1.2research.meta.ai
  2. Artificial Analysis — Muse Spark 1.2 independent evaluationartificialanalysis.ai
  3. Hacker News — Muse Code launch discussionnews.ycombinator.com
  4. Meta developer docs — pricing and rate limitsdev.meta.ai
  5. Meta — Muse Code install scriptdev.meta.ai