Anthropic 为 Claude Code 推出 Routines,可按计划任务、API 调用或事件触发执行,且运行在 Anthropic 托管基础设施上,电脑关闭后也能继续跑。
Anthropic 最近为 Claude Code 增加了 Routines 功能,核心变化是把原本“人在终端里盯着用”的 AI 编程助手,升级成可以被预先配置、自动触发、持续执行的任务系统。官方信息显示,Routines 可以在设定时间执行,也能由 API 调用或 GitHub 事件触发;更关键的是,它运行在 Anthropic 托管的基础设施上,即使本地电脑关闭,任务仍可继续进行。这意味着 Claude Code 正从交互式助手,向“云端软件工程代理”演进。
这件事重要,是因为 AI 编程工具的竞争焦点正在变化。过去大家比的是补全、改代码、修 Bug 的单点能力;现在开始比谁能接入仓库、工具链和事件流,在真实团队流程里承担持续性的工作。Routines 的出现,说明 Anthropic 想占据的不只是 IDE 入口,而是研发自动化的调度层。
对开发团队的影响很直接:重复性的巡检、修复、同步、生成文档和代码维护任务,都更容易被转成异步自动流程。对行业格局来说,这会让 AI Coding 从“副驾驶”更快走向“值班同事”,也会逼着同类产品补上计划执行、事件触发和托管运行能力。
Subscribe to ToolCenter Newsletter
Get the latest AI tool rankings, content templates, and growth experiments delivered every Friday.
Next in Deep Dives
Continue your journey

AI Video Generation Tools in 2026: Which One Actually Earns Its Bill
AI video generation in 2026 is no longer one model running away with everything. Sora 2, Veo 3, and Kling 3 are at roughly the same quality tier on cinematic shots, while Runway, Pika, Luma, Hailuo and the open-source Wan family each own a different workflow niche.

LMArena Review 2026: How the LLM Leaderboard Actually Works
LMArena (lmarena.ai) is the public-facing successor to the LMSYS Chatbot Arena — the crowdsourced benchmark that ranks large language models by blind, pairwise human votes. It is now the most-cited "real user preference" leaderboard in AI, and the rankings move markets.
