agentCLAWHUBUnverified

Long Term Memory 长期记忆

长期记忆管理系统 - 帮助AI和用户管理、存储、检索长期记忆。支持记忆分类、标签管理、重要性评分、自动压缩、跨会话记忆保持。适用于需要长期追踪信息、建立知识库、维护历史上下文的场景。 Skill: Long Term Memory 长期记忆 Owner: shenmeng Summary: 长期记忆管理系统 - 帮助AI和用户管理、存储、检索长期记忆。支持记忆分类、标签管理、重要性评分、自动压缩、跨会话记忆保持。适用于需要长期追踪信息、建立知识库、维护历史上下文的场景。 Tags: latest:2025.4.15 Version history: v2025.4.15 | 2026-04-15T05:11:17.612Z | auto No user-facing changes detected in this version. - No file changes present. - Documentation remains the same. - Behavior and features unchanged from the previous version. v4.15.0 | 2026-04-

OpenClaw

Rank

62

Safety

84

Downloads

2.2k

Updated

Oct 9, 2026

Version

2025.4.15

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 9, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 9, 2026
Adoption signal
2.2K downloadsadoption · observed Oct 9, 2026
Latest release
2025.4.15release · observed Apr 15, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s176scxxt9cxw1s0gqyexga8hd83qc4r:shenmeng-long-term-memory
  1. Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
  2. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  3. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-shenmeng-shenmeng-long-term-memory/snapshot"

Documentation

CLAWHUB

63,254 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: long-term-memory
description: 长期记忆管理系统 - 帮助AI和用户管理、存储、检索长期记忆。支持记忆分类、标签管理、重要性评分、自动压缩、跨会话记忆保持。适用于需要长期追踪信息、建立知识库、维护历史上下文的场景。
---

# Long-Term Memory 长期记忆管理

> 💰 **本 Skill 已接入 SkillPay 付费系统**
> - 每次调用费用:**0.01 USDT**
> - 支付方式:BNB Chain USDT
> - 请先确保账户有足够余额

帮助AI和用户建立持久化的长期记忆系统。

## 核心能力

1. **记忆存储** - 结构化存储重要信息、决策、上下文
2. **记忆检索** - 智能搜索和关联记忆提取
3. **记忆组织** - 分类、标签、重要性管理
4. **记忆压缩** - 自动总结和归档旧记忆
5. **记忆同步** - 跨会话保持记忆一致性

## 设计理念

> "记忆是智能的基石。没有记忆,就没有学习;没有长期记忆,就没有成长。"

### 记忆层级

```
工作记忆 (Working Memory)
    ↓ 提炼
短期记忆 (Short-term Memory) - memory/YYYY-MM-DD.md
    ↓ 归档
长期记忆 (Long-term Memory) - MEMORY.md
    ↓ 压缩
核心记忆 (Core Memory) - SOUL.md, USER.md
```

## 使用场景

| 场景 | 示例 |
|------|------|
| **个人助理** | 记录用户偏好、习惯、重要事件 |
| **项目管理** | 追踪项目决策、里程碑、经验教训 |
| **学习笔记** | 积累知识、建立知识体系 |
| **关系维护** | 记录人脉信息、互动历史 |
| **决策支持** | 保存决策依据、复盘结果 |

## 工具清单

- `memory_store.py` - 记忆存储器
- `memory_search.py` - 记忆搜索引擎
- `memory_organizer.py` - 记忆组织器
- `memory_compressor.py` - 记忆压缩器
- `memory_sync.py` - 记忆同步器

## 快速开始

### 1. 存储记忆
```bash
python scripts/memory_store.py add \
  --content "用户偏好使用微信而非邮件" \
  --category "user_preference" \
  --tags "沟通方式,偏好" \
  --importance 8
```

### 2. 搜索记忆
```bash
python scripts/memory_search.py query "用户偏好"
```

### 3. 整理记忆
```bash
python scripts/memory_organizer.py tag --importance-above 7 --add-tag "重要"
```

### 4. 压缩归档
```bash
python scripts/memory_compressor.py compress --older-than 30d --output archive.md
```

## 记忆格式

### 日常记忆 (memory/YYYY-MM-DD.md)
```markdown
# Memory Log - 2024-03-26

## Key Events
- [事件描述]
- [决策记录]
- [重要信息]

## Decisions
- [决策内容] - [原因] - [预期结果]

## Open Tasks
- [ ] [待办事项]
```

### 核心记忆 (MEMORY.md)
```markdown
# MEMORY.md - 长期记忆

## 用户偏好
- 沟通方式: 微信 > 邮件
- 工作时间: 早9晚6
- 决策风格: 数据驱动

## 重要事件
- 2024-03-15: 启动新项目X
- 2024-03-20: 完成里程碑Y

## 经验教训
- [经验总结]
```

## 参考资料

- **记忆分类法**:`references/memory-taxonomy.md`
- **压缩策略**:`references/compression-strategies.md`
- **最佳实践**:`references/best-practices.md`

---

*记住重要的,忘记琐碎的,提炼永恒的。*

_meta.json

{
  "ownerId": "kn71568gr0p3240v36pag6f7rx83qbb2",
  "slug": "shenmeng-long-term-memory",
  "version": "2025.4.15",
  "publishedAt": 1776229877612
}

references/memory-taxonomy.md

# 记忆分类法

## 记忆类型分类

### 按时间维度

| 类型 | 存储位置 | 保留周期 | 压缩策略 |
|------|---------|---------|---------|
| 工作记忆 | 会话上下文 | 当前会话 | 不保留 |
| 短期记忆 | memory/YYYY-MM-DD.md | 30天 | 压缩归档 |
| 长期记忆 | MEMORY.md | 永久 | 定期整理 |
| 核心记忆 | SOUL.md / USER.md | 永久 | 手动维护 |

### 按内容分类

#### 1. 用户偏好 (user_preference)
**定义**:关于用户喜好、习惯、风格的记忆

**示例**:
- 沟通方式偏好(微信 > 邮件)
- 工作时间习惯
- 决策风格
- 审美偏好

**存储策略**:
- 重要性:7-10
- 同步到 MEMORY.md
- 定期确认更新

#### 2. 决策记录 (decision)
**定义**:重要决策及其依据

**示例**:
- 项目技术选型
- 供应商选择
- 策略调整

**存储策略**:
- 重要性:8-10
- 记录决策原因和预期结果
- 便于后续复盘

#### 3. 重要事件 (event)
**定义**:值得记录的重要时刻

**示例**:
- 项目里程碑
- 关键会议
- 突发事件

**存储策略**:
- 重要性:6-10
- 记录时间、参与者、结果

#### 4. 任务追踪 (task)
**定义**:待办事项和进度

**示例**:
- 待完成任务
- 进行中的工作
- 阻塞事项

**存储策略**:
- 重要性:5-8
- 完成后归档

#### 5. 经验教训 (lesson)
**定义**:从实践中学习到的经验

**示例**:
- 踩过的坑
- 最佳实践
- 反模式

**存储策略**:
- 重要性:8-10
- 提炼通用性原则
- 同步到核心记忆

#### 6. 知识积累 (knowledge)
**定义**:学习到的知识点

**示例**:
- 技术知识点
- 行业洞察
- 方法论

**存储策略**:
- 重要性:6-9
- 建立知识索引

#### 7. 关系信息 (relationship)
**定义**:关于人脉关系的记忆

**示例**:
- 联系人信息
- 互动历史
- 共同经历

**存储策略**:
- 重要性:6-8
- 注意隐私保护

### 按重要性分级

| 等级 | 名称 | 描述 | 处理方式 |
|------|------|------|---------|
| 10 | 核心 | 定义性的、战略级的 | 必须记住,定期复习 |
| 9 | 重要 | 关键决策、重要事件 | 长期保留,主动回忆 |
| 8 | 显著 | 有意义的经验 | 长期保留,按需检索 |
| 7 | 有用 | 实用信息 | 中期保留,定期整理 |
| 6 | 一般 | 日常信息 | 短期保留,自动归档 |
| 5 | 普通 | 常规记录 | 短期保留,可压缩 |
| 4 | 次要 | 辅助信息 | 快速归档 |
| 3 | 轻微 | 临时信息 | 自动清理 |
| 2 | 极小 | 几乎无用 | 不保留 |
| 1 | 垃圾 | 错误/无效信息 | 立即删除 |

## 标签体系

### 系统标签
- `important` - 重要
- `urgent` - 紧急
- `decision` - 决策相关
- `user` - 用户相关
- `project:X` - 项目相关
- `person:X` - 人物相关

### 领域标签
- `tech` - 技术
- `business` - 业务
- `personal` - 个人
- `finance` - 财务
- `health` - 健康
- `learning` - 学习

### 时间标签
- `daily` - 日常
- `weekly` - 周度
- `monthly` - 月度
- `yearly` - 年度
- `milestone` - 里程碑

## 记忆生命周期

```
创建 → 活跃期 → 衰退期 → 归档期 → 清理

创建: 0-7天      → 频繁访问
活跃期: 7-30天   → 正常访问
衰退期: 30-90天  → 按需访问,开始压缩
归档期: 90天+    → 仅重要记忆保留
清理: 自动       → 低重要性记忆删除
```

## 最佳实践

### 何时存储记忆
- ✅ 用户明确说"记住这个"
- ✅ 重要决策或约定
- ✅ 重复出现的模式
- ✅ 关键错误/教训
- ✅ 用户偏好表达

### 何时不存储记忆
- ❌ 临时信息(如当前天气)
- ❌ 敏感信息(密码、隐私)
- ❌ 易变信息(实时数据)
- ❌ 冗余信息(已存储过)

### 存储原则
1. **最小必要**:只记真正重要的
2. **结构清晰**:分类+标签,便于检索
3. **定期整理**:压缩旧记忆,更新核心记忆
4. **主动遗忘**:删除过期/无效记忆

skill-card.md

## Description:

长期记忆管理系统 - 帮助AI和用户管理、存储、检索长期记忆。支持记忆分类、标签管理、重要性评分、自动压缩、跨会话记忆保持。适用于需要长期追踪信息、建立知识库、维护历史上下文的场景。

This skill is ready for commercial/non-commercial use.

## Publisher:

[shenmeng](https://clawhub.ai/user/shenmeng)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to store, search, organize, and compress durable personal or project memories across sessions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill stores durable personal or project memories on disk, including user preferences, relationships, decisions, and lessons learned.

Mitigation: Use it only with an explicit retention and deletion process, and avoid storing secrets or sensitive personal data unless retention is approved.

Risk: The artifact includes paid billing code that contacts SkillPay and an embedded billing credential.

Mitigation: Install only if paid SkillPay use is acceptable, and review or rotate the billing credential before deployment.

Risk: Bulk memory import and local memory parsing can preserve untrusted or stale content across sessions.

Mitigation: Review imported memory files before use and periodically clean or compress outdated entries.

## Reference(s):

- [Memory Taxonomy](references/memory-taxonomy.md)
- [Long Term Memory 长期记忆 on ClawHub](https://clawhub.ai/shenmeng/skills/shenmeng-long-term-memory)
- [shenmeng publisher profile](https://clawhub.ai/user/shenmeng)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [Markdown and command-line text with generated or updated local memory files]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Writes persistent memory records, summaries, and archives under the OpenClaw workspace.]

## Skill Version(s):

2025.4.15 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

requirements.txt

# Long-Term Memory 依赖

# 数据处理
python-dateutil>=2.8.0

# 可选:高级搜索
# numpy>=1.24.0
# scikit-learn>=1.3.0

# 可选:自然语言处理
# jieba>=0.42.0  # 中文分词
Github ReposUpdated 10h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/shenmeng/skills/shenmeng-long-term-memory",
      "sourceUrl": "https://clawhub.ai/shenmeng/skills/shenmeng-long-term-memory",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:13:52.934Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-shenmeng-shenmeng-long-term-memory/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-shenmeng-shenmeng-long-term-memory/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:13:52.934Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.2K downloads",
      "href": "https://clawhub.ai/shenmeng/shenmeng-long-term-memory",
      "sourceUrl": "https://clawhub.ai/shenmeng/shenmeng-long-term-memory",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:13:52.934Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2025.4.15",
      "href": "https://clawhub.ai/shenmeng/shenmeng-long-term-memory",
      "sourceUrl": "https://clawhub.ai/shenmeng/shenmeng-long-term-memory",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-15T05:11:17.612Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-shenmeng-shenmeng-long-term-memory/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-shenmeng-shenmeng-long-term-memory/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2025.4.15",
      "description": "No user-facing changes detected in this version. - No file changes present. - Documentation remains the same. - Behavior and features unchanged from the previous version.",
      "href": "https://clawhub.ai/shenmeng/shenmeng-long-term-memory",
      "sourceUrl": "https://clawhub.ai/shenmeng/shenmeng-long-term-memory",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-15T05:11:17.612Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to Long Term Memory 长期记忆 and adjacent AI workflows.