Meta has introduced a new terminal-based coding agent called Muse Code, intended to help developers tackle complex tasks across large software repositories. The tool is currently available in beta; the release was announced by Meta CEO Mark Zuckerberg in a social media post on Wednesday.
What Muse Code does
According to Zuckerberg, Muse Code can perform “complete software engineering tasks across large repos,” including planning changes, writing code, and validating results. The agent can be installed with a single command and is powered by Meta’s previously released coding model, Muse Spark.
To handle large projects, Muse Code launches its own agents that work in parallel. Zuckerberg explained: “When a job is big enough, it fans out to separate sub-agents working in parallel in isolated worktrees. Your working copy is never touched.” In testing, Meta says the system built six features for a game simultaneously without collisions.
Positioning and cost
The move aims to make Meta more competitive and potentially more affordable compared with offerings from other AI labs, such as OpenAI’s Codex and Anthropic’s Claude Code. Alexandr Wang, who leads Meta Superintelligence Labs and serves as Meta’s AI chief, told the Wall Street Journal: “We think that for a lot of workflows and a lot of use cases, this can be an incredibly good option, especially from a cost perspective.”
Broader AI strategy
Muse Code’s launch is part of Meta’s wider effort to expand its AI presence through significant investment. In June, Meta widened its focus beyond using AI primarily to support its advertising business and entered the enterprise AI market with an agent aimed at customer service and support.
Implications for developers
Muse Code could streamline work for developers handling large codebases by automating planning, code generation, and result validation without altering their local working copies. However, the tool’s real-world performance, security and legal implications, and the extent of any cost savings will be clearer only after broader adoption and independent evaluation.
