M2Wise - Memory-to-Wisdom Engine
This is a skill for the OpenClaw AI Agent to enable long-term memory and self-evolving wisdom.
🎯 Purpose
As an AI agent, you inherently lack persistent memory across distinct sessions. The M2Wise skill bridges this gap. It allows you to:
- 1. Extract and store memories (facts, preferences, commitments) from user conversations.
- Retrieve contextual memories and aggregated wisdom before answering.
- Consolidate raw memories into overarching "Wisdom" (rules, schemas, and skills) during idle time.
🚦 When to Use This Skill
You should proactively invoke this skill in the following scenarios:
- - User expresses a preference: e.g., "I prefer short answers", "Don't use emojis."
- User shares a personal fact: e.g., "I work as a Python developer", "I live in Beijing."
- User asks you to remember: e.g., "Remember that I hate spam."
- Before answering complex questions: To recall the user's past preferences or facts to personalize your response.
🛠️ How to Use (Agent Instructions)
You can interact with M2Wise via its Python SDK. Use your shell/execution environment to run these scripts snippet by snippet.
1. Installation Requirements
Make sure the environment has M2Wise installed before calling its Python API:
CODEBLOCK0
2. Saving Memories (Online Phase)
When you detect a fact or preference in the conversation, run a quick python script to save it:
CODEBLOCK1
3. Retrieving Context (Online Phase)
Before fulfilling a user's request, fetch their relevant memories:
from m2wise_sdk import M2WiseSDK
sdk = M2WiseSDK()
context = sdk.get_context("current_user_id", "How should I answer this technical question?")
print("Retrieved Context:", context)
Action: Read the output of this script and adapt your final response to the user based on the retrieved context.
4. Background Processing (Sleep & Dream)
It is a good practice to trigger memory consolidation periodically (e.g., at the end of a long task).
CODEBLOCK3
🧩 MCP Server Alternative
If your OpenClaw runtime supports MCP (Model Context Protocol), you can start the M2Wise MCP server and use its native tools instead of writing Python scripts:
CODEBLOCK4
Available MCP Tools:
- -
m2wise_add: Add memory from conversation. - INLINECODE1 : Search memories and wisdom.
- INLINECODE2 : Generate wisdom drafts.
- INLINECODE3 : Verify and publish wisdom.
🧠 Memory and Wisdom Types You Will Encounter
- - Memories:
preference (likes/dislikes), fact (states/attributes), commitment (future actions). - Wisdoms:
principle (interaction guidelines), schema (behavioral patterns), skill (operational tactics).
🚀 Best Practices
- 1. Be Proactive: Don't wait for the user to explicitly say "remember this". If they state a strong preference, save it using
sdk.add_message(). - Context First: For ambiguous requests, always query the memory bank first.
- Consolidate Often: Run
trigger_sleep() and trigger_dream() after completing a major task to ensure your wisdom evolves and stays clean.
🔗 Resources
- - GitHub Repository: https://github.com/zengyi-thinking/M2Wise.git
- Installation via OpenClaw (ClawHub):
CODEBLOCK5
技能名称: m2wise
详细描述:
M2Wise - 记忆到智慧引擎
这是OpenClaw AI Agent的一项技能，用于实现长期记忆和自我进化的智慧。
🎯 目的
作为AI Agent，你天生缺乏跨会话的持久记忆。M2Wise技能弥补了这一差距。它允许你：
- 1. 提取并存储来自用户对话的记忆（事实、偏好、承诺）。
- 检索上下文记忆和聚合的智慧后再回答。
- 整合原始记忆为更高层次的智慧（规则、模式、技能）在空闲时间。
🚦 何时使用此技能
你应在以下场景主动调用此技能：
- - 用户表达偏好：例如，我喜欢简短的回答、不要使用表情符号。
- 用户分享个人事实：例如，我是一名Python开发者、我住在北京。
- 用户要求你记住：例如，记住我讨厌垃圾邮件。
- 在回答复杂问题之前：回忆用户过去的偏好或事实，以个性化你的回复。
🛠️ 如何使用（Agent指令）
你可以通过M2Wise的Python SDK与之交互。使用你的shell/执行环境逐段运行这些脚本。
1. 安装要求
在调用M2Wise的Python API之前，确保环境已安装M2Wise：
bash
pip install m2wise[all]
2. 保存记忆（在线阶段）
当你在对话中检测到事实或偏好时，运行一个快速的Python脚本来保存它：
python
from m2wise_sdk import M2WiseSDK
sdk = M2WiseSDK()
提取并保存用户的消息
sdk.add
message(currentuser_id, 对于技术问题，我更喜欢简洁的中文回答)
3. 检索上下文（在线阶段）
在满足用户请求之前，获取他们的相关记忆：
python
from m2wise_sdk import M2WiseSDK
sdk = M2WiseSDK()
context = sdk.getcontext(currentuser_id, 我应该如何回答这个技术问题？)
print(检索到的上下文：, context)
操作：读取此脚本的输出，并根据检索到的上下文调整你对用户的最终回复。
4. 后台处理（睡眠与梦境）
定期触发记忆整合是一个好习惯（例如，在完成一个长任务后）。
python
from m2wise_sdk import M2WiseSDK
sdk = M2WiseSDK()
睡眠：提取记忆并将其分组为智慧草稿
sdk.trigger
sleep(currentuser_id)
梦境：对照反例验证草稿并发布它们
sdk.trigger
dream(currentuser_id)
🧩 MCP服务器替代方案
如果你的OpenClaw运行时支持MCP（模型上下文协议），你可以启动M2Wise MCP服务器并使用其原生工具，而不是编写Python脚本：
bash
启动MCP服务器
m2wise-mcp --data-dir ./data
可用的MCP工具：
- - m2wiseadd：从对话中添加记忆。
- m2wisesearch：搜索记忆和智慧。
- m2wisesleep：生成智慧草稿。
- m2wisedream：验证并发布智慧。
🧠 你将遇到的记忆和智慧类型
- - 记忆：preference（喜好/厌恶）、fact（状态/属性）、commitment（未来行动）。
- 智慧：principle（交互指南）、schema（行为模式）、skill（操作策略）。
🚀 最佳实践
- 1. 主动出击：不要等待用户明确说记住这个。如果他们表达了强烈的偏好，使用sdk.addmessage()保存它。
- 上下文优先：对于模糊的请求，始终先查询记忆库。
- 经常整合：在完成一个主要任务后运行triggersleep()和trigger_dream()，确保你的智慧不断进化并保持清晰。
🔗 资源
- - GitHub仓库：https://github.com/zengyi-thinking/M2Wise.git
- 通过OpenClaw（ClawHub）安装：
bash
npx clawdhub@latest install m2wise
