Chief + Muse Code: Better Together

Muse Code (`muse`) is Meta's coding agent for the terminal, running Muse models under your own Muse subscription. Chief is the management layer that puts it to work across every project you run, planning what to build, breaking goals into milestones and reviewing each result.

At a glance

CapabilityChiefMuse Code
What it isAI-native agent managerMeta's coding agent CLI for Muse models
Where it runsA dashboard above all your projectsYour terminal, in the repo you open
Models✅ Whichever agents you bring✅ Muse Wonder 1.0 and Muse Spark 1.3
Planning✅ Goal → milestones → coordinated execution✅ Works through the task you give it
Projects✅ Visibility and dispatch across projects✅ Deep focus on the repo you open
Billing✅ Free to start, bring your own agents✅ Your Muse subscription
Review✅ Auto-review against acceptance criteria✅ Changes you can inspect in your repo

What is Chief?

Chief is an AI-native agent manager. It sits above coding agents like Muse Code and handles everything between "here's what I want" and "here's the shipped result": planning what to build, figuring out what comes next, dispatching agents across your projects, and reviewing output before it ships.

Chief uses a BYOA (bring-your-own-agent) model. You connect the coding agents you already use, including Muse Code, signed in with your own Muse subscription on your own machine. No lock-in, no migration, no separate API key.


How Chief works with Muse Code

Your sign-in, your machine. Chief's relay runs Meta's official muse binary on your computer, the same way you would run it yourself. You sign in once with muse login. Chief never reads your Muse credential files.

Contributor mode off for Chief's runs. Chief starts every Muse Code run with Contributor mode turned off, so the work Chief dispatches runs on the model you picked. Your own Muse sessions keep whatever setting you chose in Muse.

Your choice of Muse model. Chief uses Muse Wonder 1.0 by default, and you can switch to Muse Spark 1.3 in Settings.

Your usage windows, visible. Muse subscriptions have a 5-hour window and a weekly window. Chief's usage card shows them as muse reports them, and Auto mode pauses when either window is used up.


What Chief adds on top

1. Plan and execute complex goals in one shot

Give Chief "add usage-based billing with team plans" and it breaks the goal into dependency-aware milestones, each with acceptance criteria and a review step. You approve the plan once; Chief dispatches Muse Code, and any other agents you use, through the whole sequence.

2. Proactive management that figures out what's next

Chief looks at project state, understands what's been completed, what's blocked, and what's ready to start, then proposes the next milestones. You make decisions; Chief keeps the pace.

3. Scale agents across your projects

Dispatch Muse Code to some repos, Claude Code or Codex to others, and see all progress in one dashboard. Chief tracks what's in flight everywhere.

4. Mix the right provider for each task

Chief's BYOA model lets you choose the agent per project or per milestone. Use Muse Code where it suits the work and keep the rest of your roster for what each agent handles best, all from a single interface.

5. Review between agent output and merge

Chief reviews every completed milestone against its acceptance criteria before marking it done, so running more agents still means reviewed output.


Getting started in 5 minutes

  1. Sign up for Chief: Free plan, no credit card required.
  2. Install Muse Code (version 1.4.7 or later) with Meta's installer, then run muse login once to sign in with your Muse subscription.
  3. Connect your coding agents: Chief uses a BYOA model. Bring Muse Code alongside Claude Code, Codex, or others.
  4. Import a project and set a goal: describe what you want accomplished in plain language.
  5. Approve the plan: Chief proposes milestones with acceptance criteria, dispatches the agents and reviews the output.

FAQ

Is Chief a replacement for Muse Code?

No. Chief manages coding agents; it doesn't replace them. Muse Code does the coding through muse. Chief does the planning, dispatching, and reviewing.

Does Chief use my Muse subscription or a separate API key?

Your subscription. Chief runs muse on your machine under the account you signed in with, so the work counts against that subscription's usage windows. No API key is needed, and Chief keeps a META_API_KEY in your shell out of its runs so they stay on your subscription.

Does Chief see my Muse credentials?

No. Chief only runs the muse commands you could run yourself. It never reads the credential files muse stores. Your prompts and code go to Meta under the terms you accepted for Muse Code, the same as when you use it directly.

Can Chief manage Muse Code alongside other agents?

Yes. Use Muse Code for some tasks and Claude Code, Codex, Qwen Code, OpenCode, Kimi Code or Gemini for others. Chief dispatches the agent you pick for each milestone from a single interface.

Can I still use Muse Code directly?

Absolutely. Chief manages background agent work; it doesn't take over your terminal. Use muse interactively anytime, and use Chief for the work you want to delegate.

See also

Chief vs Cursor

Cursor perfected the AI-enhanced IDE. Chief is what comes next — the platform for AI-native builders who manage agent teams instead of writing code by hand.

Chief vs Windsurf

Windsurf is the AI-powered IDE for interactive coding. Chief is where AI-native builders go next — managing agent teams across every project instead of coding by hand.

Chief vs Conductor

Conductor (conductor.build) runs parallel Claude Code and Codex agents on your Mac. Chief plans the work, keeps agents busy and reviews the output.

Chief vs Emdash

Emdash is old-school orchestration — you define tasks, you pick agents, you review every diff. Chief is AI-native management that proactively proposes next steps toward your goals.

Chief vs Devin

Devin is an autonomous AI engineer that handles tasks end-to-end. Chief is the management layer that coordinates multiple agents across your portfolio — planning, dispatching, and reviewing at scale.

Chief + Claude Code

Use Claude Code on many repos at once. Chief plans milestones, runs Claude Code in parallel and reviews the output, so you approve results, not prompts.

Chief + Codex

Codex is a cloud-native coding agent. Chief scales it across your portfolio — proactively planning what to build, decomposing complex goals, and mixing the right provider for each task.

Chief + Qwen Code

Qwen Code is a powerful open-weight coding agent. Chief scales it across your portfolio — proactively planning what to build, decomposing complex goals, and coordinating agents end-to-end.

Chief + OpenCode

OpenCode is a flexible open-source coding agent that works with any LLM provider. Chief scales it across your portfolio — proactively planning what to build, decomposing complex goals, and coordinating agents end-to-end.

Chief + Kimi

Kimi Code brings a 1M-token context window to your terminal on a flat subscription. Chief scales it across your portfolio — proactively planning what to build, decomposing complex goals, and coordinating agents end-to-end.

Chief + Gemini

Google's Antigravity CLI brings Gemini models to your terminal under your own Google sign-in. Chief scales it across your portfolio — proactively planning what to build, decomposing complex goals, and coordinating agents end-to-end.

Chief + Copilot

Copilot assists you in the editor and on GitHub. Chief manages the coding agents that build across your portfolio — planning, dispatching, and reviewing.

Chief + Aider

Aider is the open-source pair programmer in your terminal. Chief manages coding agents across your whole portfolio — planning, dispatching, and reviewing.

Ready to manage your agents?

_Muse and Muse Code are trademarks of Meta Platforms, Inc. Chief is an independent product and is not affiliated with, sponsored by, or endorsed by Meta._