Meta · Setup guide
How to set up Muse Code
Install the Muse Code beta on macOS or Linux, authenticate with Meta, initialise a disposable repository, and inspect its event log before granting longer-running work.
Muse Code
terminal · checked August 8, 2026
The “Open Muse Code” link goes to the vendor site. It is not an affiliate-tracked link on this page — no commission is claimed for that click. Affiliate disclosure.
Critical: finish install before closing the window
Keep the installer terminal open until you see a success message. If you used an admin window, do not close it until verification works. Then open a new Terminal or PowerShell window and run the verify step — PATH updates rarely apply to shells that were already open, especially on Windows.
Before you begin
- macOS or Linux, according to the current beta availability.
- A Meta account and a repository that can be safely used for a beta trial.
- A shell, Git, and a clean branch for the first task.
Authentication
Meta account sign-in inside the CLI
Account: Meta account with Muse Code / Model API access
Authenticate before muse init. Contributor pricing is cheaper because Meta may train on that usage and applies lower RPM limits — pick the rate deliberately for enterprise pilots.
Install or open it
1. Get the harness ready
These steps are written for beginners. On Mac, Terminal is the black/white text window where you type commands. On Windows, use PowerShell or Terminal. Use the OS tabs to hide steps that are not for your computer, then copy one command at a time.
- 01
Open Terminal on a Mac
MacClick the Spotlight search icon (magnifying glass) at the top-right of the menu bar, or press Command (⌘) + Space. Type Terminal and press Return. A text window opens — that is where you paste the install commands below. Leave it open.
- 02
Open Terminal or PowerShell on Windows
WindowsPress the Windows key, type Terminal or PowerShell, then press Enter. Use that window for the commands below. If Windows asks for permission to run a script or install software, read the prompt before approving.
- 03
How to paste a command
Copy one command at a time from this page. Click inside the terminal window, paste (Mac: ⌘+V, Windows: Ctrl+V or right-click → Paste), then press Return / Enter. Wait until the prompt comes back before running the next command. You do not need to type the leading $ if you see one in other docs.
- 04
Do not close the installer until verified
Keep the installer terminal (or admin PowerShell) open until the install finishes without errors. Closing early can leave a half-written binary or an incomplete PATH update — especially on Windows.
- 05
Open a new terminal after installers
PATH updates often only apply to new shells — especially on Windows. Do not close the install session until the installer finishes, then open a fresh Terminal/PowerShell before running --version checks.
- 06
Inspect before you pipe an installer
Commands like curl … | bash download and run a script immediately. Prefer the official package manager when offered. If you use a curl installer, you can download the script first, open it in a text editor, then run it — never paste installers from random blogs.
- 07
Install the beta (Mac / Linux)
Muse Code’s public beta path is macOS/Linux. Prefer Meta’s current product docs if the installer URL changes. Windows users should wait for official support.
bashcurl -fsSL https://dev.meta.ai/install.sh | shYou should see: The installer finishes without an error. Open a new terminal before the verify step so PATH updates apply.
Muse Code docsIf this fails
- The install command errors, or the next verify step says “command not found”. Re-run the official install command with network access, then open a brand-new terminal window before verifying.
- 08
Check the command
Open a new Terminal window, then confirm the binary before entering a real repository.
bashmuse --versionYou should see: A version string. Open a new terminal if the command is not found, then confirm Meta beta access.
Muse Code docsIf this fails
- The installer completes but muse is unavailable. Open a new shell, check the installer directory on PATH, and compare the installed command with Meta’s current instructions.
- 09
Authenticate before any repo init
Run `muse` in a disposable folder first. Complete Meta sign-in in the TUI (`/login`), or set a key with `muse auth set` / `META_API_KEY`. Do not run `muse init` on a production tree until auth succeeds.
bashmuseYou should see: The Muse TUI opens and prompts for Meta login or an API key — not an unauthenticated init.
Muse Code authenticationIf this fails
- Auth fails, the key is rejected, or the provider list is empty. Confirm the key/account is active, that you pasted the whole value, and that you are using the shell syntax for your OS (export vs $env:).
Repository or project
2. Start in the right place
Keep the first repository small, clean, and easy to roll back while you learn the harness’s permissions and context model.
- 01
Use a disposable branch
Choose a small repository or branch with tests and no production credentials.
bashgit switch -c muse-code-pilotYou should see: The prompt shows you are inside the intended folder (check with `pwd`).
If this fails
- “No such file or directory” or you are still in your home folder. Create or clone the practice folder first, then `cd` into it before starting the tool.
- 02
Initialise AGENTS.md only after auth
From the repository root, run muse init to generate AGENTS.md / project guidance. Review the file before starting agentic edits.
bashmuse initYou should see: The prompt shows you are inside the intended folder (check with `pwd`).
Muse Code configurationIf this fails
- “No such file or directory” or you are still in your home folder. Create or clone the practice folder first, then `cd` into it before starting the tool.
First run
Review the agent’s event trail
Use this task to test the workflow before handing over a larger repository or production responsibility.
- 01Ask Muse Code to explain the repository and propose one small test improvement.
- 02Allow the proposal but not a broad refactor.
- 03Review the event log, diff, and test result before trying a second task.
Why this is safe: The beta’s persistent event trail is part of the product value; the first task should test observability as well as code output.
Stop and review if
- The agent cannot show which worker or command produced a change.
- The task starts background work outside the repository boundary.
- The model or contributor data setting is unclear for the repository.
The operating boundary
Privacy, data, and cost
The setup is incomplete until you know what the harness can see, what account pays for it, and who approves a risky action.
Privacy
Muse Code offers model and contributor-data choices that need explicit review before a team trial. Contributor-tier pricing is a data trade — Meta may train on that usage and applies lower throughput limits than standard API rates.
Training on code: tier dependent
Confirm current Meta Model API and Muse Code terms for the account and region.
Sensitive repos: Start with a sanitized repository, default to standard (non-contributor) rates for confidential code, and do not connect production secrets to a beta harness.
Pricing
Free CLI; inference bills Meta Model API tokens. Contributor rates are much lower than standard and may train on usage with reduced RPM.
Model: usage based
Watch out: Contributor ~$0.10/$0.20 vs standard ~$1.25/$4.25 (confirm live rates) — the discount is a data-and-throughput trade, not a seat plan. Enterprise teams should budget standard rates unless legal approves contributor training.
When setup goes wrong
The installer completes but muse is unavailable.
Open a new shell, check the installer directory on PATH, and compare the installed command with Meta’s current instructions.
Beta access is unavailable after sign-in.
Confirm the account, region, and current beta eligibility; do not treat a successful install as proof of product access.
Background work is difficult to review.
Stop the task, inspect the event log and worktree, and reduce the task to a single foreground change.
Next steps
After the first successful run
Keep the pilot small, then compare surfaces and budget before a team rollout.
Setup details change quickly. The page was checked August 8, 2026; use the official source below before installing in a managed or production environment.