个人中心
今日签到
私信列表
消息中心
搜索全站
q_code

扫码关注官方微信
cell_code

扫码下载APP
返回顶部
技能集市 > AI智能 > layered-memory
l

layered-memory分层记忆管理

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。

作者: admin | 来源: ClawHub
下载
源自
ClawHub
版本
V 1.2.0
安全检测
已通过
279
下载量
免费
免费
0
收藏
概述
安装方式
版本历史

layered-memory

分层记忆管理系统

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。

层级说明

  • - L0（摘要）：极简摘要，节省约 99% Token
  • L1（概览）：结构概览，节省约 88% Token
  • L2（完整）：完整内容，按需加载

使用方式

bash

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

参考文档

标签

skill ai

通过对话安装

该技能支持在以下平台通过对话安装：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 layered-memory-1776115219 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 layered-memory-1776115219 技能

通过命令行安装

skillhub install layered-memory-1776115219

下载

⬇ 下载 layered-memory v1.2.0（免费）

文件大小: 30.35 KB | 发布时间: 2026-4-15 13:12

v1.2.0 最新 2026-4-15 13:12
v1.2.0: Add config loader, concurrent processing, incremental generation, dry-run mode, verbose logging. Full rewrite of generator with performance improvements. 10/10 tests passing.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

⭐ 3209 ⬇ 392958
AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

⭐ 3209 ⬇ 392957
AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

⭐ 3195 ⬇ 389589
AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

⭐ 3177 ⬇ 386644
AI智能

多链集团旗下-闲社网

闲社网热线
免费联系电话
0527-80111111
            qqline

服务时间：周一到周日 8:00-24:00

  • 公众号
    闲社 闲社线报社区
关注闲社网
  • wxkf

    闲社在线客服

  • wx

    关注闲社网微信

  • app

    闲社网APP

Archiver·手机版·闲社网·闲社论坛·羊毛社区· 多链控股集团有限公司 · 苏ICP备2025199260号-1

Powered by Discuz! X5.0   © 2024-2025 闲社网·线报更新论坛·羊毛分享社区·http://xianshe.com

p2p_official_large
返回顶部