Getting Started with Muse Code: CLI Commands, Syntax and Purpose - QAInsights
Skip to content
Share via:
Copy Link
More
In this blog post, we will see what Meta’s brand new terminal coding agent, Muse Code, actually does, how its CLI is put together, and how you can go from zero to your first agent run in about five minutes.
Meta’s Muse Code is a terminal-only coding agent built on the Muse Spark 1.2 model, which was co-trained alongside the agent itself. It offers two primary modes: an interactive TUI for development work and a headless exec mode suited for CI pipelines. Key features include persistent background subagents and a replay-exact event log that enables crash recovery.
On benchmarks, Muse Code scores below Claude Code but above Codex CLI and Grok Build, and Meta positions it primarily on cost rather than raw performance. The CLI includes commands for session management, skill extensibility, sandboxing, and cross-session messaging, with safety defaults set to on-request approval mode.
Meta just threw its hat into the AI coding agent ring today, and given how much time I have already spent living inside Claude Code and Codex CLI, I could not resist pulling apart the muse --help output the moment it dropped.
If you have used any of the other terminal agents, a lot of this will feel familiar, but Muse Code has a few design choices of its own that are worth understanding before you point it at a real repository.
Table of Contents
Toggle
What is Muse Code?
Muse Code is Meta’s first coding agent, rolled out as the company ramps up its AI investments to compete with Anthropic and OpenAI, and it is a release from Meta AI chief Alexandr Wang, who leads Meta Superintelligence Labs. It runs on a new model called Muse Spark 1.2, and this model was co-trained together with Muse Code itself, with training that included rejection sampled harness trajectories and recipe work specifically for goals, compaction, and subagents.
Two things stood out to me right away.
First , unlike Claude Code and ChatGPT Codex, Muse Code has no dedicated app interface. It lives entirely in your terminal, and that is a deliberate design choice on Meta’s part.
Second , it can run persistent background subagents that stay active for the whole session instead of spinning up fresh for every task, which Meta says cuts down on redundant information gathering and lets those subagents decide on their own when to report back to the main agent.
There is also a durability angle I really appreciate as someone who has lost long-running scripts to a bad crash before. Every model call, tool run, approval, and edit gets appended to a local event log that Meta calls replay-exact and restart-safe, so after a crash the agent picks up exactly where it left off.
On raw capability, Meta is not claiming the top spot.
On Terminal-Bench 2.1, Muse Spark 1.2 with Muse Code scored 82.9 percent, behind Claude Code on Opus 5 at 86.7 percent, but ahead of GPT-5.6 Terra on Codex at 81.8 percent and Grok Build at 81.6 percent.
On DeepSWE 1.1, the gap was similar, with Muse at 59.3 percent against 65.0 percent for Opus 5 and 64.8 percent for Codex. Meta’s pitch is not "we are smarter," it is "we are cheaper."
Wang described a contributor tier priced more than ten times cheaper than the pay-as-you-go tier, in exchange for developers opting in to let Meta use their data to improve the model.
Worth flagging for anyone comparing licensing postures too. Where OpenAI’s Codex CLI and Google’s Gemini CLI ship under the Apache 2.0 license, Muse Code stays proprietary, closer to how Anthropic runs Claude Code.
Two Ways to Run It: Interactive vs Headless
Muse Code gives you two entry points, and understanding this split early saves a lot of confusion later.
# Mode 1: Interactive TUI (no subcommand)<br>muse [OPTIONS] [PROMPT]
# Mode 2: Subcommand driven<br>muse [OPTIONS] [COMMAND_OPTIONS] [ARGS]
Run muse on its own and you land in a full screen interactive terminal UI, which is where you will do most of your actual development work. Pass a prompt straight to it, like muse "Fix the failing tests", and it kicks off a session immediately with that prompt.
The other mode is subcommand driven, and this is where exec, resume, export, skills, and the rest of the fleet live. Think of the TUI as your workbench and the subcommands as the tools you reach for when scripting or automating.
CLI Anatomy
Every command in Muse Code follows the help system consistently, as shown below.
muse --help # All commands + global options<br>muse --version # e.g. Muse Code 0.1.0<br>muse exec --help # Help for a specific command
I always run muse --help before trusting a new subcommand in a real project. It is a one second habit that has saved me from misreading a flag more than once with other CLIs.
Pro Tip: Start with muse init
? muse-demo muse init<br>Wrote AGENTS.md
? muse-demo cat AGENTS.md<br># AGENTS.md
Muse Code reads this file as project...