Meta has introduced Muse Code, a new terminal-based AI coding agent designed to help developers complete complex software engineering tasks across large code bases, as the company continues expanding its presence in the competitive AI developer tools market.
Currently available in beta, Muse Code is aimed at programmers working on large repositories and can handle tasks including planning code changes, writing new code and validating results. Meta Chief Executive Officer Mark Zuckerberg announced the release in a social media post, describing the tool as capable of completing end-to-end software engineering workflows.
The coding agent can be installed using a single command and is powered by Meta’s previously released Muse Spark coding model. According to the company, Muse Code manages large projects by automatically launching multiple AI sub-agents that work simultaneously on separate parts of the codebase.
Parallel AI agents handle large projects
Zuckerberg said that when a task becomes large enough, Muse Code distributes the work across isolated worktrees, allowing multiple AI agents to operate in parallel without modifying the developer’s main working copy. During internal testing, Meta said the system successfully built six separate features for a game at the same time without conflicts between the individual coding tasks.
Competing with AI coding tools
The launch strengthens Meta’s position in the growing market for AI-powered software development tools, where it competes with products such as OpenAI’s Codex and Anthropic’s Claude Code.
Alexandr Wang, Meta’s Chief AI Officer and head of Meta Superintelligence Labs, told The Wall Street Journal that the company believes Muse Code offers an attractive balance between performance and cost, making it suitable for a wide range of developer workflows.
Part of Meta’s broader AI expansion
Meta has significantly increased investment in artificial intelligence over the past year as it looks to expand beyond AI features supporting its advertising business. In June, the company entered the enterprise AI market with a customer service and support agent, and the introduction of Muse Code represents another step in building a broader portfolio of AI-powered productivity tools for developers and businesses.
