Anthropic 发布常驻智能体构建指南，详解事件收件箱与记忆机制
Anthropic 把自家跑常驻智能体的经验拆成了收件箱、定时器、记忆这几个可落地的模块。和网上零散的教程比，这是官方一手方法论。正在搭自动化智能体的工程师可以直接对照着补架构短板。
Anthropic 发布了一份关于构建常驻（always-on）智能体的官方指南，收录于 claude.com 的文章资源区。指南围绕四个核心原语展开：事件收件箱（event inbox）、定时器（timers）、记忆（memory）等。事件收件箱用于接收和整理外部触发的输入，定时器让智能体具备主动行动能力而不只是被动响应。记忆部分强调跨会话的连续性，确保智能体在长期运行中不丢失上下文。这类内容延续了 Anthropic 在智能体工程方向的经验沉淀，对需要搭建长期运行智能体的开发者有直接参考价值。
指南的核心思路是把智能体从“一问一答”改成持续在线的事件驱动架构：外部事件先进收件箱排队，定时器触发周期性任务，记忆负责在多次运行间保持状态。相比单次调用的聊天模式，这种架构适合监控、自动化巡检等场景。开发者可以直接对照指南检查自己的智能体缺少哪些原语。
Banger new guide from Anthropic. It discusses the core primitives of always-on agents. It covers the importance of an event inbox, using timers for proactive capabilities, ensuring continuity with memory, and more. Read more: claude.com/resources/arti…📊 20 ⚡
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Anthropic, Claude, agents, MCP and tools.
Source attribution: curated from elvis (@omarsar0). Cross-source corroboration: 11 independent sources have covered this development (including 小互, AI Will, Databricks), confirming industry-wide signal strength.
