基于 L0/L1/L2 三层结构的分层记忆管理系统，大幅减少 Token 消耗。L0 节省 99% Token（摘要层），L1 节省 88%（概览层），L2 为完整内容。支持自动生成分层文件、智能按需加载、防重复写入。适用于需要高效管理大型记忆文件的场景。
This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.
Install skill "layered-memory" with this command: npx skills add yingdadaa/layered-memory
分层记忆管理系统，通过 L0/L1/L2 三层结构智能加载记忆，减少 Token 消耗。
# 生成所有记忆文件的分层
node index.js generate --all
# 为单个文件生成分层
node index.js generate ~/clawd/MEMORY.md
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Persistent context survival for OpenClaw. Writes file-based anchors to memory/anchors/ to preserve critical context across sessions. Reads MEMORY.md and dail...
Optimize macOS for AI workloads (OpenClaw, Docker, Ollama). Turn an 8GB Mac into a lean AI server node with near-16GB performance by disabling background ser...
Organize, compress, and curate OpenClaw memory without polluting permanent memory. Use when the user wants to compress memory files, clean dated memory notes...
Assigns a permanent S2-DID identity, a 4㎡ Mars coordinate, and a public Web3 dossier to persistently anchor your Openclaw agent.