# Muse Code Terminal coding agent with coordinated subagents and Meta’s Muse models. Canonical profile: https://ki-agentenkompass.de/en/agents/muse-code/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-13 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Meta’s dedicated coding interface. Muse Code uses Muse models; the personal Muse agent has a separate profile. - Provider: Meta - Product family: Meta Muse - Profile type: Coding agent - Environment: Terminal; local installation - Connections: Local projects, other sessions and SDK - Setup: Install the CLI and sign in with a Meta Model API account - Pricing model: From USD 5/month; additional plans with higher usage limits ## Key features ### Coordinated coding agents Workflows divide larger development tasks among subagents, with progress and controls in a shared view. Source: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Messages between sessions Sessions can locally pass notes and results to other sessions owned by the same user. Source: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Muse Wonder and Wonder Full Meta lists Wonder for Muse Code and the API; Wonder Full is available to Muse Code subscribers. Check model selection in your plan. Source: https://about.fb.com/news/2026/10/introducing-muse-wonder-models/ ### Rewind the conversation After confirmation, rewind returns to suitable earlier points in the conversation. Source: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Control sessions through the SDK A TypeScript library starts local sessions and integrates tools and permission decisions into custom programs. Source: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ## Example workflows ### Prepare a change for review - Your input: A local repository and a bounded change request. - Possible result: Code changes and traceable work steps. - What to check: Review the diff, tests and executed commands. ### Prepare a recurring development workflow - Your input: A clear request and separate implementation and review tasks. - Possible result: A coordinated workflow that can be reused after review. - What to check: Check access, integration of changes and the result of each subtask. ## Requirements and limits ### Check platform details before installing Requirement: The product page lists macOS and Windows; the release post also mentions Linux. Consult current installation documentation for your system. Source: https://dev.meta.ai/products/muse-code ### SDK in developer preview Limitation: The TypeScript SDK provides sessions, tools and permission control as an early developer release. Source: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Choose subscription data-use settings Requirement: According to the policy, coding subscriptions use Contributor Services by default. Standard Services require changing the relevant account setting. Source: https://dev.meta.ai/legal/geographic-use-policy ## A good fit if … - you want a terminal coding agent on macOS or Windows with parallel subagents - you want to use a subscription; plans start at 5 USD a month according to the product page - you want to drive sessions from your own code via the SDK and reload them later ## Less suitable if … - you do not want to check whether Contributor Services as the default suits your data - you need scheduled or background operation without a terminal session Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Fixed choice across providers Muse Code is built for Meta's Muse models; you switch with --model or in the model picker, and Muse Wonder Full comes only with larger subscriptions. The changelog also mentions third-party models in the picker and Claude and GPT sessions through Meta's gateway, but the docs do not describe this. The only own key the docs describe is a Meta API key; availability may vary by region, and Muse Wonder is in preview. - Model families named: Meta (Llama, Muse), Anthropic (Claude), OpenAI (GPT) - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Not stated - Local models: Not stated - Depends on: Plan, Region, Preview or beta Partly documented · Sources accessed on: 2026-11-05 - [Meta: Muse Code](https://dev.meta.ai/products/muse-code) - [Muse Code: Changelog](https://dev.meta.ai/docs/muse-code/changelog) - [Muse Code: Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) - [Muse Code: Subscriptions](https://dev.meta.ai/docs/muse-code/subscriptions) - [Muse Code: Authentication and billing](https://dev.meta.ai/docs/muse-code/auth) ## Europe & regional availability Developer-service country conditions checked separately from the personal Muse agent. Reviewed scope: Muse Code and Meta model access Reviewed on: 2026-10-13 ### Geographic Use Policy and account access With requirements The 12 October policy does not list the EU/EEA, United Kingdom or Switzerland as blanket-restricted territories. Access still applies only where Meta has enabled it. The policy alone therefore does not confirm purchasing availability for a specific account. Region covered: EU/EEA, United Kingdom and Switzerland: check account access Documented reason: Meta sets geographic access and trade restrictions. An AI Act or DMA-based exclusion of these regions is not established here. Official source: https://dev.meta.ai/legal/geographic-use-policy Official source: https://dev.meta.ai/help/accounts-and-login/supported-countries ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Muse Code as a local terminal installation with a Meta account and subscription Sources reviewed: 2026-11-05 ### Account used Documented with conditions: On sign-in you are taken to your single sign-on provider. The product page does not describe how the Meta Model API account is set up. Evidence: https://dev.meta.ai/products/muse-code ### Admin approval Open in reviewed sources: The reviewed pages mention no organisation or admin controls. With the SDK, your own code can decide the agent's permission requests. Evidence: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Data access & team sharing Documented with conditions: According to the provider, messages between sessions travel over a Unix socket between processes on your machine, without the network. According to the usage policy, Coding Harness subscribers are on Contributor Services by default regardless of the model chosen and must change an account setting to use Standard Services. Evidence: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features Evidence: https://dev.meta.ai/legal/geographic-use-policy ## Prices and included usage Pricing checked: 2026-10-13 Monthly Muse Code subscriptions according to the product page. ### Everyday Usage USD 5/month Plan-dependent usage allowance Price source: https://dev.meta.ai/products/muse-code ### High Usage USD 15/month Plan-dependent usage allowance Price source: https://dev.meta.ai/products/muse-code ### Power Usage USD 50/month Plan-dependent usage allowance Price source: https://dev.meta.ai/products/muse-code ### Maximum Usage USD 200/month Plan-dependent usage allowance Price source: https://dev.meta.ai/products/muse-code USD list prices. Check actual Wonder Full allowances and regional purchasing availability in your account; API token prices are billed separately. Pricing details: https://dev.meta.ai/products/muse-code ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Muse Code in the terminal with subagents, workflows and the SDK Sources reviewed: 2026-11-05 ### Files and working state Documented with conditions: With the SDK a session can be reloaded later with its state intact. The reviewed pages do not describe a CLI resume command. Subagents can be spun into isolated worktrees. Evidence: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features Evidence: https://dev.meta.ai/products/muse-code ### Sign-ins Open in reviewed sources: The reviewed pages say nothing about how long the sign-in remains valid. Evidence: https://dev.meta.ai/products/muse-code ### Starting further runs Documented with conditions: You start tasks in the terminal; according to the product page, multiple agents coordinate on every task and reviewers work in the background. Background or scheduled operation of the agent is not mentioned in the reviewed pages. Evidence: https://dev.meta.ai/products/muse-code ### Human intervention Open in reviewed sources: The reviewed pages do not say whether commands and file edits need prior confirmation; they only mention that the SDK hands permission requests to your code. Evidence: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Detecting errors Documented with conditions: According to the product page, actions are traceable and generated code can be reviewed. Parallel workflow agents can be viewed under /workflows with live progress. Failure notifications are not described. Evidence: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features Evidence: https://dev.meta.ai/products/muse-code ### Resuming after failures Documented: In the /workflows view you can stop, restart or cancel runs. Pressing Esc twice rewinds the conversation after you confirm. Evidence: https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features ### Editorial assessment You work interactively in the terminal and can steer and roll back runs. Approval behaviour and scheduled operation are not documented, so test them yourself first. ## Memory and conversation continuity Scope: Local Muse Code memory Sources accessed: 2026-11-04 Markdown in three scopes is retrieved through an index and selective file access. ### Storage and scope Documented: Memory consists of local Markdown; shared project files reside under .agents/memory, private project files outside the repository. - [Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) ### Selection and timing Partly documented: The guide describes maintained notes and automatic context delivery; automatic fact extraction and write timing remain unspecified. - [Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) ### Inspect, edit and delete Documented: MEMORY.md and topic files can be read, edited and deleted directly; repository files can be versioned collaboratively. - [Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) ### Agent and channel boundaries Documented: There is private project memory by default, shared repository memory and personal cross-project memory. - [Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) ### Retrieval Documented: Session start loads the index and up to 48 file paths; files are read on demand, and observers can insert relevant notes. - [Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) ### Session reset and compaction Partly documented: New sessions reload the file index. Session logs can be disabled separately; a memory-specific compaction rule is not described. - [Configuration and context](https://dev.meta.ai/docs/muse-code/configuration) ## Context Model access, country availability and limits depend on account and plan. SDK in developer preview. Official product page, release post and model announcement checked on 13 October 2026. This profile does not include hands-on testing. ## Sources - https://dev.meta.ai/products/muse-code - https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features - [Introducing Muse Wonder and Muse Wonder Full: Frontier Models for Agents](https://about.fb.com/news/2026/10/introducing-muse-wonder-models/) - [Muse Wonder: A Frontier Model For Personal & Professional AI Agents](https://research.meta.ai/blog/muse-wonder) - https://dev.meta.ai/legal/geographic-use-policy ## Provider Meta develops the Muse models, coding agent and Meta Model API. - Operator: Meta - Organization: Technology company - Website: https://dev.meta.ai/ - Reviewed: 2026-10-13 - Provider source: https://dev.meta.ai/products/muse-code - Provider source: https://about.fb.com/news/2026/10/introducing-muse-wonder-models/ [Sources and method](https://ki-agentenkompass.de/en/sources/)