Meta launches Muse Code, an AI agent for large code bases

Meta launches Muse Code, an AI agent for large code bases
Meta expanded its AI coding offerings with a new agent that, it promises, can handle complex tasks with complex software.

<p id="speakable-summary" class="wp-block-paragraph">Meta, considered a bit of a straggler in the AI harnesses realm, is making strides to catch up. This week, the company released a new terminal coding agent aimed at programmers looking for assistance with complex tasks across large software code bases. </p>
<p class="wp-block-paragraph">Muse Code, which is currently available in beta, can accomplish “complete software engineering tasks across large repos,” Meta CEO Mark Zuckerberg said <a rel="nofollow" href="https://x.com/finkd/status/2085080750034940201?s=20">in a social media</a> post on Wednesday. Those tasks include “planning changes, writing code, validating the results,” he added. </p>
<p class="wp-block-paragraph">Code, which can be installed with a single command, is powered by Meta’s previously released coding model, Muse Spark. It handles large projects by launching its own agents, which then work simultaneously.</p>
<p class="wp-block-paragraph">“When a job is big enough, it fans out to separate sub-agents working in parallel in isolated worktrees,” Zuckerberg explained. “Your working copy is never touched. In testing we had it build six features for a game simultaneously with no collisions.”</p>
<p class="wp-block-paragraph">The move attempts to position Meta more competitively, and more affordably, with AI Lab peers like OpenAI and its coding agent Codex, and Anthropic with Claude Code.</p>
<p class="wp-block-paragraph">“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,” Alexandr Wang, Meta’s AI chief, who leads Meta Superintelligence Labs, <a rel="nofollow" href="https://www.wsj.com/tech/ai/meta-releases-coding-agent-to-compete-with-openai-and-anthropic-af87b517?mod=e2twd">told</a> the Wall Street Journal. </p>
<p class="wp-block-paragraph">Meta has been attempting to grow its AI presence by <a rel="nofollow" href="https://www.reuters.com/business/meta-narrows-annual-capex-forecast-ai-buildout-grows-2026-07-29/">pouring money</a> into development. In June, it expanded beyond its core focus of using AI to support its advertising business and <a href="https://www.reuters.com/business/meta-launches-enterprise-focused-ai-business-agent-automate-daily-operations-2026-06-03/" target="_blank" rel="noreferrer noopener nofollow">entered the enterprise AI market</a> with an agent aimed customer service and support. </p>