# Muse Code

Meta's terminal-based AI coding agent with persistent async background agents

**Verdict: conditional.** Meta's first coding agent and a credible beta entry with genuinely novel architecture — persistent background agents, worktree-isolated sub-agent fan-out, and a crash-safe event log. Powered by the co-trained Muse Spark 1.2, it lands second only to Claude Opus 5 on Meta's own published benchmarks. Vendor-run numbers, beta status, and closed-source binary distribution temper the promise. Best for developers evaluating coding agents who want to test persistent-context architecture and aggressive contributor-tier pricing. Last verified 2026-08-06.

Muse Code is Meta Superintelligence Labs' terminal-based AI coding agent, launched in beta on August 5, 2026. It handles complete software engineering tasks across large repositories — planning changes, writing code, and validating results — powered by the co-trained Muse Spark 1.2 model.

Its headline architectural differentiator is persistent async background agents that stay alive for the entire session rather than spawning fresh per task, building up repository context over time to reduce latency and manual steering. For large tasks, Muse Code fans out to parallel sub-agents working in isolated Git worktrees, so the developer's working copy is never touched.

Every model call, tool run, approval, and edit is appended to a local append-only event log before it executes, making the runtime replay-exact and crash-safe — if Muse Code crashes 20 hours into a long-running task, it resumes precisely where it stopped with no lost work and no re-prompting.

Muse Code ships with bundled skills: /plan turns a task into an approval-gated plan, /grill stress-tests that plan, and /goal drives toward completion of a stated objective. Available on macOS and Linux via a one-line curl installer. Competes directly with Anthropic's Claude Code, OpenAI's Codex, and Google's Antigravity CLI.

## Strengths

- Persistent multi-step coding sessions — background agents retain repo context across tasks, avoiding redundant exploration and reducing steering
- Long-horizon autonomous tasks — event-log crash recovery enables 24-hour runs; agent resumes precisely where it stopped with no lost work
- Parallel feature work — worktree-isolated sub-agents build multiple features simultaneously without collisions (Meta demoed six game features in parallel)
- Cost-sensitive experimentation — contributor tier at ~$0.10 input / $0.20 output per 1M tokens undercuts every comparable coding agent
- Multimodal repo work — accepts video fly-throughs and images as coding context; no incumbent terminal agent ships this as a first-class flow
- Production workflows requiring independently verified benchmarks — all published results are vendor-run in Meta's framework with no third-party reproduction
- Windows development — macOS and Linux only at beta launch; no Windows build exists
- Open-source or self-hosted pipelines — closed-source binary installed via shell script; no public repository, API-dependent, no weight access
- Teams with strict data governance — contributor tier sends prompts and completions to Meta's training pipeline; opting out costs 12.5x more on input

## Pricing

- Model: paid
- Standard: $1.25 in / $4.25 out per 1M tokens
- Contributor: $0.10 in / $0.20 out per 1M tokens

Website: https://dev.meta.ai

## Sources

- [The Register — Meta wants to get inside your terminal with its new coding agent](https://www.theregister.com/ai-and-ml/2026/08/06/meta-wants-to-get-inside-your-terminal-with-its-new-coding-agent/5283717)
- [Meta AI Research Blog — Muse Code and Muse Spark 1.2 announcement (official)](https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2)
- [Engadget — Meta introduces Muse Code, its take on a coding agent](https://www.engadget.com/2231285/meta-introduces-muse-code-its-take-on-a-coding-agent/)
- [Meta — Muse Code product page (official)](https://developer.meta.com/ai/products/muse-code/)
- [Meta — Muse Code documentation (official)](https://dev.meta.ai/docs/muse-code)
- [MarkTechPost — Meta AI Releases Muse Code (Beta)](https://www.marktechpost.com/2026/08/05/meta-superintelligence-labs-releases-muse-code/)
- [VentureBeat: Meta enters AI coding wars](https://venturebeat.com/orchestration/meta-enters-the-ai-coding-wars-with-muse-spark-1-2-and-muse-code-with-persistent-async-background-agents)
- [Meta Model API docs: pricing and rate limits (no Muse Spark Open price listed)](https://dev.meta.ai/docs/pricing-rate-limits)
- [Vorp Labs — Muse Spark 1.2 release review](https://vorplabs.com/models/releases/muse-spark-1-2)
- [explainx.ai — Muse Code Beta](https://www.explainx.ai/blog/meta-muse-code-coding-agent-muse-spark-1-2-launch-august-2026)
- [TechCrunch: Meta launches Muse Code](https://techcrunch.com/2026/08/05/meta-launches-muse-code-an-ai-agent-for-large-code-bases/)

Canonical: https://neomanex.com/directory/muse-code