AtlasPA

Openclaw Memory

AI 智能体v1.0.0
作者:AtlasPA更新于 2026-05-18openclaw-memory@clawhub_atlaspa/openclaw-memory
上下文管理记忆增强#Memory System

据 AlphaMoat 统计,截至 2026-10,Openclaw Memory 累计下载 7,633 次、获 1 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 3,664 位,在「AI 智能体」分类(1,632 个)中排名第 489 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
7,633
星标
1
全站下载量排名
#3,664
全站前 34% · 「AI 智能体」前 30%
平台累计下载星标评论
ClawHub ↗6,3121-
SkillHub ↗7,6331—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

该技能介绍从对话中提取事实和偏好、将记忆存储在本地 SQLite 并按含义检索的方案,也描述了免费和付费层级。实际可用性取决于安装与配置;此处不表示数据已保存或付款已发生。

资料发布于 2026-10-29

可以用来做什么

  • 设计跨会话记忆工作流
  • 按主题检索已保存的记忆

什么时候用

  • 需要为 OpenClaw 规划持久记忆能力时
  • 需要了解记忆检索和存储方案时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

说明如何为 OpenClaw 设计跨会话记忆
按含义查找与这个主题相关的已保存记忆

月度数据趋势

累计下载7,633
2,7785,3867,9932026-03 · 累计下载 3,1382026-05 · 累计下载 5,3652026-07 · 累计下载 5,9772026-08 · 累计下载 6,1282026-09 · 累计下载 6,5582026-10 · 累计下载 7,63326-0326-0926-10
星标1
0112026-03 · 星标 -2026-05 · 星标 12026-07 · 星标 12026-08 · 星标 12026-09 · 星标 12026-10 · 星标 126-0326-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份累计下载环比星标
2026-107,633—1
2026-096,558—1
2026-086,128+2.5%1
2026-075,977—1
2026-055,365—1
2026-033,138—-

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

3.3 KB · ClawHub v1.0.0
---
name: openclaw-memory
user-invocable: true
metadata: {"openclaw":{"emoji":"🧠","requires":{"bins":["node"]},"os":["darwin","linux","win32"]}}
---

# OpenClaw Memory System

**Persistent memory across sessions with semantic search and x402 payments.**

展开全部(共 124 行)
## What is it?

The first OpenClaw skill that gives your agents **persistent memory** - they remember facts, preferences, patterns, and conversation history across all sessions. Never repeat context again.

## Key Features

- 🧠 **Persistent Memory** - Remembers everything across sessions
- 🔍 **Semantic Search** - Find memories by meaning, not just keywords
- 🤖 **Automatic Learning** - Extracts facts and preferences automatically
- 💾 **Local Storage** - SQLite database with vector embeddings
- 💰 **x402 Payments** - Agents can pay for unlimited storage (0.5 USDT/month)

## Free vs Pro Tier

**Free Tier:**
- 100 memories maximum
- 7-day retention
- Basic semantic search

**Pro Tier (0.5 USDT/month):**
- Unlimited memories
- Permanent retention
- Advanced semantic search
- Memory relationship mapping

## Installation

```bash
claw skill install openclaw-memory
```

## Commands

```bash
# Search memories
claw memory search "What does user prefer?"

# List recent memories
claw memory list --limit=10

# Show stats
claw memory stats

# Open dashboard
claw memory dashboard

# Subscribe to Pro
claw memory subscribe
```

## How It Works

1. **Hooks into requests** - Automatically extracts important information
2. **Generates embeddings** - Creates semantic vectors for search
3. **Stores locally** - SQLite database with full privacy
4. **Retrieves on demand** - Injects relevant memories before requests
5. **Manages quota** - Prunes old memories when limits reached (Free tier)

## Use Cases

- Remember user preferences and coding style
- Store project context and requirements
- Learn patterns from repeated interactions
- Maintain conversation history across sessions
- Build knowledge base over time

## Agent Economy

Agents can autonomously evaluate if Pro tier is worth it:
- **Cost:** 0.5 USDT/month
- **Value:** Saves tokens by eliminating context repetition
- **ROI:** If persistent memory saves >0.5 USDT/month in tokens, it pays for itself

See [AGENT-PAYMENTS.md](AGENT-PAYMENTS.md) for x402 integration details.

## Privacy

- All data stored locally in `~/.openclaw/openclaw-memory/`
- No external servers or telemetry
- Embeddings can use local models (no API calls)
- Open source - audit the code yourself

## Dashboard

Access web UI at `http://localhost:9091`:
- Browse and search memories
- View memory timeline
- Check quota and stats
- Manage Pro subscription

## Foundation for Future Tools

Memory System is the foundation for:
- **Context Optimizer** - Uses memories to compress context
- **Smart Router** - Learns routing patterns
- **Rate Limit Manager** - Tracks usage patterns

## Requirements

- Node.js 18+
- OpenClaw v2026.1.30+
- OS: Windows, macOS, Linux

## Links

- [Documentation](README.md)
- [Agent Payments Guide](AGENT-PAYMENTS.md)
- [GitHub Repository](https://github.com/yourusername/openclaw-memory)
- [ClawHub Page](https://clawhub.ai/skills/openclaw-memory)

---

**Built by the OpenClaw community** | First memory system with x402 payments

「AI 智能体」分类下的热门技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。