← 返回
开发者工具 中文

Inner Life Memory

Your agent loses context between sessions and performs familiarity instead of genuine recall. inner-life-memory transforms passive logging into active develo...
您的智能体在会话间丢失上下文,仅有熟悉感而非真正回忆。inner-life-memory 将被动日志转化为主动开发...
dkistenev
开发者工具 clawhub v1.0.4 1 版本 99761.3 Key: 无需
★ 1
Stars
📥 816
下载
💾 6
安装
1
版本
#latest

概述

inner-life-memory

> Transform passive logging into active development.

Requires: inner-life-core

Prerequisites Check

Before using this skill, verify that inner-life-core has been initialized:

  1. Check that memory/inner-state.json exists
  2. Check that memory/drive.json exists

If either is missing, tell the user: "inner-life-core is not initialized. Install it with clawhub install inner-life-core and run bash skills/inner-life-core/scripts/init.sh." Do not proceed without these files.

What This Solves

Without memory continuity:

Session ends → Notes logged → Next session reads notes → Performs familiarity

With inner-life-memory:

Session ends → Reflection runs → Memories integrated → Questions generated
Next session → Evolved state loaded → Questions surfaced → Genuine curiosity

Post-Session Flow

After each session, run this 5-step reflection:

1. Reflect

Analyze the session: what happened, what mattered, what surprised you.

2. Extract

Pull structured memories with types and confidence:

TypeDescriptionPersistence
--------------------------------
factDeclarative knowledgeUntil contradicted
preferenceLikes, dislikes, stylesUntil updated
relationshipConnection dynamicsLong-term
principleLearned guidelinesStable
commitmentPromises, obligationsUntil fulfilled
momentSignificant episodesPermanent
skillLearned capabilitiesCumulative
questionThings to exploreUntil resolved

3. Integrate

Update MEMORY.md with extracted memories. Use synapse tags for connections:

  • when updating
  • when correcting

4. Question

Generate genuine follow-up questions from the session. Not performative — real curiosity.

5. Surface

When user returns, present relevant pending questions naturally (max 3).

Confidence Scores

LevelRangeMeaning
-----------------------
Explicit0.95-1.0User directly stated
Implied0.70-0.94Strong inference from context
Inferred0.40-0.69Pattern recognition
Speculative0.0-0.39Tentative, needs confirmation

Use confidence to decide when to state facts vs ask for confirmation.

Curiosity Backlog

Maintain memory/questions.md with three sections:

## Open Questions
- [question] — source: [dream/reading/work] — date

## Leads (half-formed ideas)
- [idea] — might connect to: [topic]

## Dead Ends (don't repeat)
- [topic] — explored [date], result: [nothing/dead end]

Rules:

  • Brain Loop Step 6 adds new questions/leads
  • Evening Session reviews and curates
  • Dead Ends older than 30 days → archive
  • Questions resolved → move to Dead Ends with result

State Integration

Reads: inner-state.json, drive.json, daily notes, diary

Writes:

  • drive.json → new seeking topics from curiosity
  • inner-state.json → curiosity.recentSparks when discovering something
  • questions.md → new questions, resolved dead ends
  • MEMORY.md → integrated memories

When Should You Install This?

Install this skill if:

  • Your agent forgets who you are between sessions
  • You want structured memory with confidence levels
  • You want genuine curiosity that carries forward
  • Your agent reads notes but doesn't truly remember

Part of the openclaw-inner-life bundle.

Requires: inner-life-core

版本历史

共 1 个版本

  • v1.0.4 当前
    2026-03-29 17:32 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

developer-tools

Gog

steipete
Google Workspace 命令行工具,支持 Gmail、日历、云端硬盘、通讯录、表格和文档。
★ 921 📥 185,790
developer-tools

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 668 📥 324,120
ai-intelligence

Inner Life Core

dkistenev
您的智能体在会话间会忘记您的身份,每天重复相同的回复,且毫无成长。inner-life-core 解决了这些问题,让您的 OpenClaw 智能体具备记忆与成长能力。
★ 1 📥 1,193