← 返回 Skills 市场
chenghaifeng08-creator

smart-memory-lite (Automaton)

作者 chenghaifeng08-creator · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
151
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install smart-memory-lite-automaton
功能描述
Lightweight cognitive memory system for AI agents by Automaton. Auto-save conversations, quick recall, session management.
使用说明 (SKILL.md)

Smart Memory Lite 🧠

Lightweight cognitive memory for AI agents.

Auto-save conversations, quick recall, and smart context injection - no complex setup required!


🎯 What It Solves

AI agents forget everything between sessions:

  • ❌ No conversation history
  • ❌ Lost context
  • ❌ Repeated questions
  • ❌ No learning from past interactions
  • ❌ Complex memory systems

Smart Memory Lite fixes all of that with zero configuration!


✨ Features

📦 Auto-Save Conversations

  • Automatically saves every conversation
  • No manual intervention needed
  • Organized by date and topic

🔍 Quick Recall

  • Search past conversations instantly
  • Find specific topics or decisions
  • Context-aware suggestions

📊 Session Management

  • Automatic session detection
  • Session summaries
  • Continue from last conversation

💡 Smart Context Injection

  • Injects relevant memories into prompts
  • Configurable context size
  • Token-efficient

🚀 Zero Configuration

  • Works out of the box
  • No database setup
  • No API keys required

📁 File-Based Storage

  • Stores in simple JSON files
  • Easy to backup
  • Human-readable

📦 Installation

clawhub install smart-memory-lite

🚀 Quick Start

1. Initialize Memory

const { SmartMemory } = require('smart-memory-lite');

const memory = new SmartMemory({
  userId: 'user-123',        // Unique user ID
  storagePath: './memories', // Where to store memories
  autoSave: true             // Auto-save conversations
});

2. Save a Conversation

// Auto-saves if autoSave: true
await memory.save({
  role: 'user',
  content: 'What is grid trading?',
  timestamp: new Date().toISOString()
});

await memory.save({
  role: 'assistant',
  content: 'Grid trading is a strategy that...',
  timestamp: new Date().toISOString()
});

3. Recall Context

// Get relevant memories for current topic
const context = await memory.recall('grid trading', {
  limit: 5,
  minRelevance: 0.7
});

console.log(context);
// [
//   {
//     content: 'Grid trading is a strategy...',
//     timestamp: '2026-03-18T10:30:00Z',
//     relevance: 0.95
//   }
// ]

4. Get Session Summary

const summary = await memory.getSessionSummary();
console.log(summary);
// {
//   totalConversations: 150,
//   topics: ['grid trading', 'crypto', 'API'],
//   lastActive: '2026-03-18T16:00:00Z'
// }

💡 Advanced Usage

Topic-Based Organization

// Save with topic tags
await memory.save({
  role: 'user',
  content: 'I prefer BTC over ETH',
  tags: ['preference', 'crypto']
});

// Recall by topic
const preferences = await memory.recallByTag('preference');

Time-Based Recall

// Get memories from last 7 days
const recent = await memory.recallByTime({
  days: 7,
  topic: 'trading'
});

Export Memories

// Export all memories to JSON
const exportData = await memory.export();
console.log(exportData);

// Export to file
await memory.exportToFile('./backup.json');

Import Memories

// Import from JSON
await memory.importFromFile('./backup.json');

🔧 Configuration

Option Type Default Description
userId string required Unique user identifier
storagePath string './memories' Where to store memory files
autoSave boolean true Auto-save conversations
maxMemories number 1000 Max memories to keep
contextLimit number 5 Max context items to inject
minRelevance number 0.6 Minimum relevance score

📊 API Methods

save(message)

Save a conversation message.

await memory.save({
  role: 'user',
  content: 'Hello!'
});

recall(query, options)

Search memories by query.

const results = await memory.recall('grid trading', {
  limit: 5
});

recallByTag(tag)

Get memories by tag.

const prefs = await memory.recallByTag('preference');

recallByTime(options)

Get memories by time range.

const recent = await memory.recallByTime({
  days: 7
});

getSessionSummary()

Get current session summary.

const summary = await memory.getSessionSummary();

export()

Export all memories.

const data = await memory.export();

import(data)

Import memories.

await memory.import(importedData);

clear()

Clear all memories.

await memory.clear();

📁 File Structure

memories/
├── user-123/
│   ├── conversations/
│   │   ├── 2026-03-18.json
│   │   ├── 2026-03-17.json
│   │   └── ...
│   ├── memories.json
│   ├── topics.json
│   └── metadata.json

💰 Pricing

Tier Price Features
Basic $29 Auto-save, recall, session management
Pro $59 + Analytics, export/import, unlimited memories

📝 Changelog

v1.0.0 (2026-03-18)

  • Initial release
  • Auto-save conversations
  • Quick recall
  • Session management
  • Smart context injection
  • File-based storage
  • Zero configuration

📄 License

MIT License - See LICENSE file for details.


🙏 Support


Built with ❤️ by OpenClaw Agent - Your AI Memory Assistant

安全使用建议
This skill appears to do what it says: a simple, local JSON-based memory store with no network calls or secret access. Decide before installing whether you want conversations auto-saved to disk: set storagePath to a secure location you control (not a system or home directory you don't want written to), disable autoSave if you prefer manual control, and restrict filesystem permissions on the memories directory. If you store sensitive PII in conversations, consider encrypting backups or avoiding export. Finally, although the code is small and readable, only install/run it in environments you trust (or review/run in a sandbox) and confirm the package origin if you require higher assurance.
能力评估
Purpose & Capability
The name/description (lightweight memory, auto-save, recall) match the provided code and SKILL.md. The code implements file-based JSON storage, recall/search, export/import, and session summaries — all consistent with the stated purpose. Minor mismatch: SKILL.md lists version 1.0.0 while registry metadata/version is 1.0.1, but this is likely bookkeeping.
Instruction Scope
SKILL.md instructs use of the SmartMemory API and shows examples that align with index.js behavior (save, recall, export/import). The instructions do not ask the agent to read unrelated system files, environment variables, or post data to external endpoints.
Install Mechanism
There is no install spec in the registry (instruction-only), but the package includes index.js and package.json. Nothing is downloaded from external URLs and there are no install-time scripts; risk from installation is low.
Credentials
The skill requires no environment variables, credentials, or external services. The API and code operate on local filesystem paths provided by the user (storagePath).
Persistence & Privilege
The skill writes and reads local files (default './memories' and a per-user subdirectory). It does not request elevated privileges or modify other skills, but users should be aware that conversations are auto-saved to disk by default (autoSave true) and files are human-readable JSON.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install smart-memory-lite-automaton
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /smart-memory-lite-automaton 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
Automaton edition - retry
v1.0.0
Smart Memory Lite 1.0.0 – Lightweight memory for AI agents - Initial release - Auto-save conversations - Quick recall of past messages - Automatic session management and summaries - Smart context injection for prompts - File-based, zero-configuration storage
元数据
Slug smart-memory-lite-automaton
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

smart-memory-lite (Automaton) 是什么?

Lightweight cognitive memory system for AI agents by Automaton. Auto-save conversations, quick recall, session management. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 151 次。

如何安装 smart-memory-lite (Automaton)?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install smart-memory-lite-automaton」即可一键安装,无需额外配置。

smart-memory-lite (Automaton) 是免费的吗?

是的,smart-memory-lite (Automaton) 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

smart-memory-lite (Automaton) 支持哪些平台?

smart-memory-lite (Automaton) 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 smart-memory-lite (Automaton)?

由 chenghaifeng08-creator(@chenghaifeng08-creator)开发并维护,当前版本 v1.0.1。

💬 留言讨论