\n<\/p>\n
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>\n
Muse Code, which is currently available in beta, can accomplish \u201ccomplete software engineering tasks across large repos,\u201d Meta CEO Mark Zuckerberg said in a social media<\/a> post on Wednesday. Those tasks include \u201cplanning changes, writing code, validating the results,\u201d he added.<\/p>\n Code, which can be installed with a single command, is powered by Meta\u2019s previously released coding model, Muse Spark. It handles large projects by launching its own agents, which then work simultaneously.<\/p>\n \u201cWhen a job is big enough, it fans out to separate sub-agents working in parallel in isolated worktrees,\u201d Zuckerberg explained. \u201cYour working copy is never touched. In testing we had it build six features for a game simultaneously with no collisions.\u201d<\/p>\n 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>\n \u201cWe 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,\u201d\u00a0Alexandr Wang, Meta\u2019s AI chief who leads Meta Superintelligence Labs,\u00a0told<\/a> the Wall Street Journal.<\/p>\n Meta has been attempting to grow its AI presence by pouring money<\/a> into development. In June, it expanded beyond its core focus of using AI to support its advertising business and entered the enterprise AI market<\/a>\u00a0with an agent aimed at customer service and support.<\/p>\n<\/div>\n