Meta launches Muse Code, a persistent multi-agent rival to Claude Code and Codex

Mark Zuckerberg's terminal agent uses persistent subagents and Muse Spark 1.2 to plan, edit and validate code.

By · Published · Updated

Primary source: X

Why it matters

Muse Code moves Meta from supplying AI models to owning the developer workflow, where persistent agents, audit logs and parallel execution are becoming core infrastructure.

Meta launches Muse Code to run long software tasks across large repositories — Mark Zuckerberg's terminal agent uses persistent subagents and Muse Spark 1.2 to plan, edit and validate code.

Mark Zuckerberg (@finkd) launched Meta's Muse Code in beta on August 5th, giving developers a terminal-based agent designed to plan, execute and validate software engineering work across large repositories.

Muse Code is Meta's first dedicated coding agent built around the Muse model family. The release moves Meta beyond selling model access through an API and into the application layer, where Anthropic, OpenAI, Google and Cursor are competing to control how developers delegate work to AI.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.