Memory Enhancement

Name: Memory Enhancement
Rating: 3.5 (1 reviews)
Author: cv-forever

By cv-forever 👁 21 views ▲ 0 votes

OpenClaw memory enhancement plugin: BGE-M3 based long-term memory retrieval

GitHub

Install

pip install -r

README

# Memory Enhancement Plugin

BGE-M3 based long-term memory enhancement plugin for OpenClaw.  
Automatically retrieves relevant historical memories and injects them into conversation context.

## Features

- **Automatic memory retrieval** — On each session start, queries the BGE-M3 API server for memories relevant to the current context, injects them into `before_prompt_build`
- **Long-term memory storage** — `add_memories` tool to save important conversations, decisions, and discoveries
- **Memory search** — `retrieve_memories` tool to query stored memories on demand
- **Configurable** — threshold, topK, cache, debug logging, all tunable via OpenClaw plugin config

## How it works

```
Session Start
  │
  ▼
before_prompt_build hook
  │
  ├── Extract recent conversation text
  ├── Query BGE-M3 API (POST /retrieve)
  ├── Inject top-K relevant memories into prompt
  │
  ▼
Agent response with memory context
```

## Installation

```bash
openclaw plugins install @cv/memory-enhancement
openclaw gateway restart
```

## Configuration

| Field        | Default   | Description                          |
|-------------|-----------|--------------------------------------|
| enabled     | true      | Enable/disable the plugin            |
| apiHost     | 127.0.0.1 | BGE-M3 API server host               |
| apiPort     | 8080      | BGE-M3 API server port               |
| threshold   | 0.5       | Similarity threshold (0.0–1.0)       |
| topK        | 3         | Max memories to inject               |
| timeout     | 15000     | API call timeout (ms)                |
| maxRetries  | 2         | Max retries on failure               |
| cacheEnabled| true      | Enable query cache                   |
| cacheTTL    | 300       | Cache TTL (seconds)                  |
| debug       | false     | Verbose debug logging                |

## Prerequisites

- BGE-M3 API server running on the configured host:port
- OpenClaw >= 2026.4.0

## Server Setup

Memory Enhancement 插件需要一个 BGE-M3 API 服务端来提供记忆检索能力。

服务端代码和部署说明在仓库的 [`server/`](server/) 目录中：

```bash
cd server
pip install -r requirements.txt
python3 memory_api_server_mac.py --port 8080
```

详见 [server/README.md](server/README.md)。

如果需要训练自己的 LoRA 适配器，请参考原始项目仓库（包含完整训练脚本、数据预处理流程和评估工具）。

## Version

**1.0.1** — Added server setup documentation

## Author

小爪 🐾

tools