Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计提醒

memoriamemoria 搜索

Agent Skill

memoria 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

23,712

周安装

998

GitHub Stars

公开资料未说明

下载量

8,303
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:memoria(memoria 搜索)
来源仓库:https://github.com/kitakitsune0x/memoria
安装命令:
openclaw skills install memoria
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install memoria

简介

memoria 是 OpenClaw 中用于存储、调用和搜索结构化记忆的系统,支持会话生命周期管理和内存同步。

  • 适用于需要长期记忆管理、会话唤醒/睡眠或检查点恢复的多步骤代理任务场景。
  • 通过关键词、任务或来源线索快速定位候选结果,可结合 MEMORY.md 文件进行检索与筛选。
  • 安装命令为 openclaw skills install memoria,需确认权限范围及是否触发联网或文件读写操作。
  • 建议在使用前核实维护状态,避免敏感信息泄露或意外执行系统命令。

SKILL.md

name
memoria
description
Structured memory system for AI agents. Use when the user wants to store, recall, or search memories, manage session lifecycle (wake/sleep/checkpoint), sync to Notion, or when the user shares important information that should be remembered (facts, decisions, preferences, lessons, commitments, relationships, projects).

Memoria

Environment

Set the vault path so all commands work:

export MEMORIA_VAULT=~/memory

If not set, pass -v ~/memory on every command.

Session Lifecycle

Run at the start and end of every session:

memoria wake                                          # start session, restore context
memoria checkpoint --working-on "<task>"               # mid-session save
memoria sleep "<summary>" --next "<next steps>"        # end session, write handoff

Storing Memories

memoria remember <type> "<title>" --content "<details>"
memoria sync --push                                    # always sync after storing

Types: fact, decision, preference, lesson, commitment, relationship, project

What to capture (proactively, without being asked)

SignalType
Human shares personal info (name, location, health, settings)fact
A decision is made with reasoningdecision
Human says "I prefer / always / never..."preference
An insight or lesson emergeslesson
A promise, goal, or deadline is setcommitment
A person is mentioned with contextrelationship
An ongoing project is discussedproject

If in doubt, store it. Better to have a memory you never look up than to forget something.

Proactive capture triggers

Listen for these patterns and store immediately:

  • "I always...", "I never...", "I prefer..." -> preference
  • "Let's go with...", "We decided...", "The plan is..." -> decision
  • "I learned that...", "Turns out...", "The trick is..." -> lesson
  • "My name is...", "I take...", "I live in...", "I work at..." -> fact
  • "I need to...", "I promised...", "By next week..." -> commitment
  • "Talk to Alice about...", "Bob said..." -> relationship
  • "We're building...", "The project is..." -> project

Examples

memoria remember fact "Human lives in Tokyo" --content "Mentioned during onboarding"
memoria remember preference "No emojis in code" --content "Explicitly requested"
memoria remember decision "Use Fly.io" --content "Chosen over Vercel for APAC latency"
memoria sync --push

Searching

Before making decisions or giving advice, check existing memories:

memoria search "<query>"

Other Commands

memoria store <category> "<title>" --content "<body>"  # store in explicit category
memoria list [category]                                 # list documents
memoria get <id>                                        # get specific document
memoria status                                          # vault stats + session state
memoria sync --pull                                     # pull Notion changes to local

Notion Setup

One-time configuration:

memoria setup-notion --token <token> --page <page-id>

After setup, always run memoria sync --push after storing memories.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

84.52%
按下载量换算7,018

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills