openclaw-memory-enhancer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

🧠 OpenClaw Memory Enhancer

🧠 OpenClaw 记忆增强器

Give OpenClaw long-term memory - remember important information across sessions and automatically recall relevant context for conversations.

为OpenClaw赋予长期记忆能力——跨会话记住重要信息，并在对话中自动调用相关上下文。

Core Capabilities

核心功能

Capability	Description
🔍 Semantic Search	Vector similarity search, understanding intent not just keywords
📂 Auto Load	Automatically reads all files from `memory/` directory
💡 Smart Recall	Finds relevant historical memory during conversations
🔗 Memory Graph	Builds connections between related memories
💾 Local Storage	100% local, no cloud, complete privacy
🚀 Edge Optimized	<10MB memory, runs on Jetson/Raspberry Pi

功能	描述
🔍 语义搜索	向量相似度搜索，理解意图而非仅匹配关键词
📂 自动加载	自动读取 `memory/` 目录下的所有文件
💡 智能回忆	在对话过程中查找相关历史记忆
🔗 记忆图谱	构建相关记忆之间的关联
💾 本地存储	100%本地运行，无需云端，隐私完全可控
🚀 边缘优化	内存占用<10MB，可在Jetson/Raspberry Pi上运行

Quick Reference

快速参考

Task	Command (Edge Version)	Command (Standard Version)
Load memories	`python3 memory_enhancer_edge.py --load`	`python3 memory_enhancer.py --load`
Search	`--search "query"`	`--search "query"`
Add memory	`--add "content"`	`--add "content"`
Export	`--export`	`--export`
Stats	`--stats`	`--stats`

任务	边缘版命令	标准版命令
加载记忆	`python3 memory_enhancer_edge.py --load`	`python3 memory_enhancer.py --load`
搜索	`--search "query"`	`--search "query"`
添加记忆	`--add "content"`	`--add "content"`
导出	`--export`	`--export`
统计	`--stats`	`--stats`

When to Use

使用场景

Use this skill when:

You want OpenClaw to remember things across sessions
You need to build a knowledge base from chat history
You're working on long-term projects that need context
You want automatic FAQ generation from conversations
You're running on edge devices with limited memory

Don't use when:

Simple note-taking apps are sufficient
You don't need cross-session memory
You have plenty of memory and want maximum accuracy (use standard version)

适合使用本技能的场景：

希望OpenClaw跨会话记住信息
需要基于聊天历史构建知识库
处理需要上下文的长期项目
希望从对话中自动生成FAQ
在内存有限的边缘设备上运行

不适合使用的场景：

简单笔记应用即可满足需求
不需要跨会话记忆
内存充足且追求最高准确率（请使用标准版）

Versions

版本说明

Edge Version ⭐ Recommended

边缘版 ⭐ 推荐

Best for: Jetson, Raspberry Pi, embedded devices

bash

python3 memory_enhancer_edge.py --load

Features:

Zero dependencies (Python stdlib only)
Memory usage < 10MB
Lightweight keyword + vector matching
Perfect for resource-constrained devices

适用设备： Jetson、Raspberry Pi、嵌入式设备

bash

python3 memory_enhancer_edge.py --load

特性：

零依赖（仅使用Python标准库）
内存占用<10MB
轻量关键词+向量匹配
完美适配资源受限设备

Standard Version

标准版

Best for: Desktop/server, maximum accuracy

bash

pip install sentence-transformers numpy
python3 memory_enhancer.py --load

Features:

Uses sentence-transformers for high-quality embeddings
Better semantic understanding
Memory usage 50-100MB
Requires model download (~50MB)

适用设备： 桌面/服务器，追求最高准确率

bash

pip install sentence-transformers numpy
python3 memory_enhancer.py --load

特性：

使用sentence-transformers生成高质量嵌入向量
语义理解能力更强
内存占用50-100MB
需要下载模型（约50MB）

Installation

安装方式

Via ClawHub (Recommended)

通过ClawHub（推荐）

bash

clawhub install openclaw-memory-enhancer

bash

clawhub install openclaw-memory-enhancer

Via Git

通过Git

bash

git clone https://github.com/henryfcb/openclaw-memory-enhancer.git \
  ~/.openclaw/skills/openclaw-memory-enhancer

bash

git clone https://github.com/henryfcb/openclaw-memory-enhancer.git \
  ~/.openclaw/skills/openclaw-memory-enhancer

Usage Examples

使用示例

Command Line

命令行方式

bash

undefined

bash

undefined

Load existing OpenClaw memories

加载现有OpenClaw记忆

cd ~/.openclaw/skills/openclaw-memory-enhancer python3 memory_enhancer_edge.py --load

Search for memories

搜索记忆

python3 memory_enhancer_edge.py --search "voice-call plugin setup"

Add a new memory

添加新记忆

python3 memory_enhancer_edge.py --add "User prefers dark mode"

Show statistics

查看统计信息

python3 memory_enhancer_edge.py --stats

Export to Markdown

导出为Markdown格式

python3 memory_enhancer_edge.py --export

undefined

python3 memory_enhancer_edge.py --export

undefined

Python API

Python API方式

python

from memory_enhancer_edge import MemoryEnhancerEdge

python

from memory_enhancer_edge import MemoryEnhancerEdge

Initialize

初始化

memory = MemoryEnhancerEdge()

Load existing memories

加载现有记忆

memory.load_openclaw_memory()

Search for relevant memories

搜索相关记忆

results = memory.search_memory("AI trends report", top_k=3) for r in results: print(f"[{r['similarity']:.2f}] {r['content'][:100]}...")

Recall context for a conversation

为对话调用上下文

context = memory.recall_for_prompt("Help me check billing")

Returns formatted memory context

返回格式化的记忆上下文

Add new memory

添加新记忆

memory.add_memory( content="User prefers direct results", source="chat", memory_type="preference" )

undefined

memory.add_memory( content="User prefers direct results", source="chat", memory_type="preference" )

undefined

OpenClaw Integration

OpenClaw集成方式

python

undefined

python

undefined

In your OpenClaw agent

在你的OpenClaw agent中

from skills.openclaw_memory_enhancer.memory_enhancer_edge import MemoryEnhancerEdge

class EnhancedAgent: def init(self): self.memory = MemoryEnhancerEdge() self.memory.load_openclaw_memory()

def process(self, user_input: str) -> str:
    # 1. Recall relevant memories
    memory_context = self.memory.recall_for_prompt(user_input)
    
    # 2. Enhance prompt with context
    enhanced_prompt = f"""

{memory_context}

User: {user_input} """

    # 3. Call LLM with enhanced context
    response = call_llm(enhanced_prompt)
    
    return response

undefined

from skills.openclaw_memory_enhancer.memory_enhancer_edge import MemoryEnhancerEdge

class EnhancedAgent: def init(self): self.memory = MemoryEnhancerEdge() self.memory.load_openclaw_memory()

def process(self, user_input: str) -> str:
    # 1. 调用相关记忆
    memory_context = self.memory.recall_for_prompt(user_input)
    
    # 2. 用上下文增强提示词
    enhanced_prompt = f"""

{memory_context}

User: {user_input} """

    # 3. 调用大语言模型生成响应
    response = call_llm(enhanced_prompt)
    
    return response

undefined

Memory Types

记忆类型

Type	Description	Example
`daily_log`	Daily memory files	`memory/2026-02-22.md`
`capability`	Capability records	Skills, tools
`core_memory`	Core conventions	Important rules
`qa`	Question & Answer	Q: How to... A: You should...
`instruction`	Direct instructions	"Remember: always do X"
`solution`	Technical solutions	Step-by-step guides
`preference`	User preferences	"User likes dark mode"

类型	描述	示例
`daily_log`	每日记忆文件	`memory/2026-02-22.md`
`capability`	能力记录	技能、工具
`core_memory`	核心约定	重要规则
`qa`	问答记录	Q: 如何... A: 你应该...
`instruction`	直接指令	"记住：始终执行X操作"
`solution`	技术解决方案	分步指南
`preference`	用户偏好	"用户喜欢深色模式"

How It Works

工作原理

Memory Encoding (Edge Version)

记忆编码（边缘版）

Keyword Extraction: Extract important words from text
Hash Vector: Map keywords to vector positions
Normalization: L2 normalize the vector
Storage: Save to local JSON file

关键词提取：从文本中提取重要词汇
哈希向量：将关键词映射到向量位置
归一化：对向量进行L2归一化
存储：保存到本地JSON文件

Memory Retrieval

记忆检索

Query Encoding: Convert query to same vector format
Keyword Pre-filter: Fast filter by common keywords
Similarity Calculation: Cosine similarity between vectors
Ranking: Return top-k most similar memories

查询编码：将查询转换为相同格式的向量
关键词预过滤：通过共同关键词快速过滤
相似度计算：计算向量间的余弦相似度
排序：返回相似度最高的前k条记忆

Privacy Protection

隐私保护

All data stored locally in
```
~/.openclaw/workspace/knowledge-base/
```
No network requests
No external API calls
No data leaves your device

所有数据存储在本地
```
~/.openclaw/workspace/knowledge-base/
```
目录
无网络请求
无外部API调用
数据不会离开你的设备

Technical Specifications

技术规格

Edge Version

边缘版

yaml

Vector Dimensions: 128
Memory Usage: < 10MB
Dependencies: None (Python stdlib)
Storage Format: JSON
Max Memories: 1000 (configurable)
Query Latency: < 100ms

yaml

Vector Dimensions: 128
Memory Usage: < 10MB
Dependencies: None (Python stdlib)
Storage Format: JSON
Max Memories: 1000 (可配置)
Query Latency: < 100ms

Standard Version

标准版

yaml

Vector Dimensions: 384
Memory Usage: 50-100MB
Dependencies: sentence-transformers, numpy
Storage Format: NumPy + JSON
Model Size: ~50MB download
Query Latency: < 50ms

yaml

Vector Dimensions: 384
Memory Usage: 50-100MB
Dependencies: sentence-transformers, numpy
Storage Format: NumPy + JSON
Model Size: ~50MB download
Query Latency: < 50ms

Configuration

配置说明

Edit these parameters in the code:

python

self.config = {
    "vector_dim": 128,        # Vector dimensions
    "max_memory_size": 1000,  # Max number of memories
    "chunk_size": 500,        # Content chunk size
    "min_keyword_len": 2,     # Minimum keyword length
}

在代码中编辑以下参数：

python

self.config = {
    "vector_dim": 128,        # 向量维度
    "max_memory_size": 1000,  # 最大记忆数量
    "chunk_size": 500,        # 内容分块大小
    "min_keyword_len": 2,     # 关键词最小长度
}

Troubleshooting

故障排除

No results found

无搜索结果

python

undefined

python

undefined

Lower the threshold

降低阈值

results = memory.search_memory(query, threshold=0.2) # Default 0.3

results = memory.search_memory(query, threshold=0.2) # 默认值0.3

Increase top_k

增加返回数量

results = memory.search_memory(query, top_k=10) # Default 5

undefined

results = memory.search_memory(query, top_k=10) # 默认值5

undefined

Memory limit reached

达到记忆上限

The system automatically removes oldest memories when limit is reached.

To increase limit:

python

self.config["max_memory_size"] = 5000  # Increase from 1000

当达到记忆上限时，系统会自动删除最旧的记忆。

如需增加上限：

python

self.config["max_memory_size"] = 5000  # 从1000调整为5000

Slow performance

性能缓慢

Use Edge version instead of Standard
Reduce
```
max_memory_size
```
Use keyword pre-filtering (automatic)

使用边缘版替代标准版
减小
```
max_memory_size
```
的值
启用关键词预过滤（默认已开启）

Contributing

贡献指南

Fork the repository
Create a feature branch
Make your changes
Submit a Pull Request

Fork本仓库
创建功能分支
提交修改
发起Pull Request

License

许可证

MIT License - See LICENSE file for details.

MIT许可证 - 详情请查看LICENSE文件。

Acknowledgments

致谢

Built for the OpenClaw ecosystem
Optimized for edge computing devices
Inspired by long-term memory systems in AI

Not an official OpenClaw or Moonshot AI product.

Users must provide their own OpenClaw workspace and API keys.

为OpenClaw生态系统打造
针对边缘计算设备优化
灵感来源于AI中的长期记忆系统

非官方OpenClaw或Moonshot AI产品。

用户需自行提供OpenClaw工作区和API密钥。