據 AlphaMoat 統計,截至 2026-09,Openclaw Mem0 累計下載 3,203 次、獲 4 個星標,在全部 5,078 個 AI 技能中排名第 3,553 位,在「AI 智慧體」分類(969 個)中排名第 725 位。
| 平台 | 累計安裝 | 累計下載 | 星標 | 評論 |
|---|---|---|---|---|
| ClawHub ↗ | 106 | 3203 | 4 | 2 |
各平台的計數口徑不同,統計時間不一致。
主文說明可在每輪前自動檢索並注入記憶、在每輪後自動捕獲資訊,也提供手動儲存、搜尋、讀取、列出和刪除記憶的工具。自動捕獲可能儲存敏感聊天內容;雲端服務或跨使用者記憶配置不當可能洩露資訊。啟用前應明確捕獲規則,敏感對話時預設關閉自動捕獲,並按使用者或租戶隔離憑據與記憶範圍。刪除操作前確認目標記錄,定期審閱自動召回內容。
資料釋出於 2026-10-29
以下是根據技能文件生成的示例,不代表實際執行結果。
2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。
| 月份 | 累計下載 | 環比 | 星標 |
|---|---|---|---|
| 2026-09 | 3203 | — | 4 |
| 2026-08 | 3113 | +3.5% | 4 |
| 2026-07 | 3008 | +8.9% | 4 |
| 2026-06 | 2762 | +6.3% | 4 |
| 2026-05 | 2599 | — | 4 |
| 2026-03 | 1726 | — | 4 |
以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。
# OpenClaw Mem0 Plugin Mem0 integration for OpenClaw. Adds intelligent long-term memory to your agents, allowing them to remember user preferences, facts, and past conversations automatically. ## When to use - You want your agent to remember user details (name, job, preferences) across sessions - You need "infinite context" by retrieving relevant past interactions - You want to build a personalized assistant that learns over time - You need both cloud (managed) and self-hosted (local) memory options
## Setup
### Platform Mode (Recommended)
1. Get a free API key at [mem0.ai](https://mem0.ai)
2. Add to your OpenClaw config:
```json
{
"plugins": {
"entries": {
"openclaw-mem0": {
"enabled": true,
"config": {
"mode": "platform",
"apiKey": "your-mem0-api-key",
"userId": "default-user"
}
}
}
}
}
```
### Open-Source Mode (Self-Hosted)
Connect to your own Mem0 instance (requires `mem0ai` package installed):
```json
{
"plugins": {
"entries": {
"openclaw-mem0": {
"enabled": true,
"config": {
"mode": "open-source",
"oss": {
"vectorStore": {
"provider": "chroma",
"config": {
"collectionName": "memories",
"path": "./chroma_db"
}
}
}
}
}
}
}
}
```
## Usage
This plugin works automatically (Zero-Shot) but also provides manual tools.
### Automatic Features
- **Auto-Recall**: Before every agent turn, it searches memory for relevant context and injects it into the system prompt.
- **Auto-Capture**: After every agent turn, it analyzes the conversation and stores key facts into memory.
### Manual Tools
The agent can proactively call these tools:
| Tool | Description | Parameters |
|------|-------------|------------|
| `memory_store` | Explicitly save a fact | `text` (string), `longTerm` (bool) |
| `memory_search` | Search memories | `query` (string), `scope` ("session"\|"long-term") |
| `memory_get` | Get memory by ID | `memoryId` (string) |
| `memory_list` | List all memories | `userId` (string) |
| `memory_forget` | Delete a memory | `memoryId` (string) or `query` (string) |
### Example
**User**: "I'm moving to Tokyo next month."
*Agent automatically captures this fact.*
**(Two weeks later)**
**User**: "What's a good restaurant for my farewell dinner?"
*Agent automatically recalls "User is moving to Tokyo" and suggests a restaurant in their current city.*
## Plugin structure
```
openclaw-mem0/
package.json # NPM package config (@xray2016/openclaw-mem0)
index.ts # Plugin implementation & tools
lib/ # Internal Mem0 client implementation
SKILL.md # This file
README.md # Detailed documentation
```
## Author
Maintained by @xRay2016. Modified from the original Mem0 OpenClaw integration.
將開發過程中的經驗、錯誤與修正記錄為 Markdown 檔案,供日後重用並提升為工作區記憶。
用自然語言描述需求,在本機與遠端技能市場尋找技能並取得推薦。
給 AI agent 用的瀏覽器自動化命令列技能。
將使用者明確糾正與自我檢視整理成分層記憶,並依使用情況升級或封存。
在安裝第三方技能之前,按清單審查來源、許可權與危險模式的技能。
將代理記憶與跨技能狀態整理成具型別與約束的知識圖譜。
規劃 AI 代理主動跟進、工作記憶與回顧流程的工作區設定指南。
指導如何建立與更新有效 Claude 技能的寫作指南。
資料月份:2026-09 · 下載/星標/安裝數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。