Skip to main content

Meta Unleashes Muse Code: AI for Huge Codebases

Meta, previously perceived as somewhat behind in the realm of advanced AI tools, is now making substantial progress to close that gap. This week, the

2 min read102 views5 tags
Originally reported bytechcrunch

Meta, previously perceived as somewhat behind in the realm of advanced AI tools, is now making substantial progress to close that gap. This week, the company unveiled a new terminal coding agent, specifically designed to empower programmers by providing assistance with intricate tasks across vast software codebases.

Currently available in beta, this new tool, named Muse Code, is capable of executing “complete software engineering tasks across large repos,” as stated by Meta CEO Mark Zuckerberg in a social media announcement on Wednesday. He further elaborated that these tasks include “planning changes, writing code, [and] validating the results.”

The Muse Code agent, which facilitates installation with a single command, is powered by Meta’s previously introduced coding model, Muse Spark. It adeptly manages extensive projects by initiating its own specialized sub-agents, which then operate in parallel.

Zuckerberg explained the system’s efficiency, noting, “When a job is big enough, it fans out to separate sub-agents working in parallel in isolated worktrees.” He also assured users of data integrity, stating, “Your working copy is never touched,” and cited successful internal testing where the agent “build six features for a game simultaneously with no collisions.”

This strategic launch positions Meta more competitively and affordably against its prominent AI lab counterparts, such as OpenAI with its Codex coding agent and Anthropic with Claude Code.

Alexandr Wang, Meta’s AI chief and leader of Meta Superintelligence Labs, conveyed to 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.”

Meta has consistently been injecting significant capital into development to expand its AI footprint. In June, the company broadened its focus beyond using AI primarily for its advertising business, making a notable entry into the enterprise AI market with an agent tailored for customer service and support applications.

#AI News#Meta#Muse Code#Coding Agent#Large Codebases
ES
Editorial StaffEditor

The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.

View all posts
Reader feedback

What did you think of this story?

User Comments

Filter:
No comments yet. Be the first to comment!
Continue reading
View all news