内容来源：https://techcrunch.com/2026/08/05/meta-launches-muse-code-an-ai-agent-for-large-code-bases/

内容总结：

Meta在人工智能编程工具领域正加速追赶。本周，该公司推出了一款全新的终端编程代理，旨在帮助程序员处理大型软件代码库中的复杂任务。这款名为Muse Code的工具目前处于测试阶段，可通过单条命令安装，其底层由Meta此前发布的编程模型Muse Spark驱动。

Meta首席执行官马克·扎克伯格在周三的社交媒体帖子中表示，Muse Code能够“在大型代码库中完成完整的软件工程任务”，包括“规划更改、编写代码、验证结果”。他解释道，当任务规模足够大时，该工具会派出多个子代理，在隔离的工作树中并行作业，“你的工作副本绝不会被改动。在测试中，它同时为游戏构建了六项功能，且未发生任何冲突。”

此举旨在让Meta在AI编程领域与OpenAI的Codex、Anthropic的Claude Code等竞争对手展开更具性价比的竞争。Meta人工智能负责人、负责Meta Superintelligence Labs的亚历山大·王向《华尔街日报》表示：“我们认为，对于许多工作流程和使用场景，尤其是从成本角度来看，这可以是一个极其出色的选择。”

近年来，Meta持续加大AI研发投入以扩展其AI版图。今年6月，该公司在利用AI支持广告业务的核心方向之外，还进军企业AI市场，推出了一款面向客户服务与支持场景的代理工具。

中文翻译：

Meta在人工智能编程工具领域曾被视作稍显落后，但如今正加速追赶。本周，该公司发布了一款新的终端编码代理，面向在大型软件代码库中处理复杂任务时寻求帮助的程序员。

Meta首席执行官马克·扎克伯格周三在社交媒体发帖称，目前处于测试阶段的Muse Code能够“在大型代码库中完成完整的软件工程任务”。他补充说，这些任务包括“规划变更、编写代码、验证结果”。

Code可通过单条命令安装，由Meta先前发布的编码模型Muse Spark驱动。它通过启动自身的多个代理来处理大型项目，这些代理随后并行工作。

扎克伯格解释：“当任务规模足够大时，它会分派给在隔离工作树中并行运行的多个子代理。你的工作副本绝不会被触碰。在测试中，我们让它同时为一款游戏构建了六个功能，且没有任何冲突。”

此举旨在让Meta在人工智能实验室同行（如OpenAI及其编码代理Codex、Anthropic的Claude Code）面前更具竞争力，同时在价格上更具优势。

Meta人工智能负责人、领导Meta超级智能实验室的王亚历山大（Alexandr Wang）告诉《华尔街日报》：“我们认为，对于许多工作流程和用例来说，这可能是一个极佳的选择，尤其是从成本角度而言。”

Meta一直在通过大量投入资金来扩大其人工智能版图。今年6月，该公司在核心业务——用人工智能支持广告业务——之外进一步拓展，凭借一款面向客户服务和支持的代理进入了企业人工智能市场。

英文来源：

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.
Muse Code, which is currently available in beta, can accomplish “complete software engineering tasks across large repos,” Meta CEO Mark Zuckerberg said in a social media post on Wednesday. Those tasks include “planning changes, writing code, validating the results,” he added.
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.
“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.”
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.
“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, told the Wall Street Journal.
Meta has been attempting to grow its AI presence by pouring money into development. In June, it expanded beyond its core focus of using AI to support its advertising business and entered the enterprise AI market with an agent aimed at customer service and support.