目录

1. manus context

上下文为王：深入剖析 Manus 背后的上下文工程哲学 深入探讨由 Manus 团队开创的 AI Agent 上下文工程原则。我们分析了其关键策略，从 KV 缓存优化到错误处理，并评估了这些策略对构建如 Manus 一般高效、强大的 AI Agent 的深远影响。 https://manus.guide/zh-CN/blog/context-engineering-for-ai-agents/

manus context 笔记

2. Context Engineering for Agents

Notion A tool that connects everyday work into one space. It gives you and your teams AI tools—search, writing, note-taking—inside an all-in-one, flexible workspace. https://www.notion.so/Context-Engineering-for-Agents-2a1808527b17803ba221c2ced7eef508

Principle Claude Code Manus Deep AgentsCLI
Offload context Use filesystem Yes Yes (E2B) Yes
Enable user memories Yes (CLAUDE.md) Yes Yes (memoriesdir,agent.md)
Minimize tools Yes (~12) Yes (<20) Yes (11)
Give agent computer (bash tool) Yes Yes Yes
Progressive disclosure of actions Yes (skills) Yes WIP
Reduce context Compaction Yes Yes No
Summarization Yes Yes Yes
Isolate context Sub-agents Yes Yes Yes

3. Effective context engineering for AI agents

Effective context engineering for AI agents \ Anthropic Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems. https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents