Meta launches Muse Code, a terminal AI coding agent

Meta this week released Muse Code, a new terminal coding agent aimed at programmers who need help with complex tasks across large software code bases. Currently available in beta, Muse Code can be installed with a single command and is powered by Meta’s previously released coding model, Muse Spark.

Muse Code can complete software engineering tasks across large repositories — including planning changes, writing code, and validating the results, Meta CEO Mark Zuckerberg said in a social media post on Wednesday. It handles large projects by launching its own agents, which then work simultaneously. “When a job is big enough, it fans out to separate sub-agents working in parallel in isolated worktrees,” Zuckerberg said. “Your working copy is never touched. In testing we had it build six features for a game simultaneously with no collisions.”

The launch positions Meta more competitively, and more affordably, against AI lab peers like OpenAI, with its Codex coding agent, and Anthropic, with Claude Code. Alexandr Wang, Meta’s AI chief who leads Meta Superintelligence Labs, told the Wall Street Journal the tool could be a strong option for many workflows and use cases, particularly on cost.

Meta has been pouring money into AI development to grow its presence in the field. In June, it expanded beyond its core focus of using AI to support its advertising business, entering the enterprise AI market with an agent aimed at customer service and support.

Why it matters

Muse Code is Meta’s attempt to compete on developer tooling and price against Anthropic and OpenAI’s coding agents, an area where Meta has lagged despite its broader AI spending.