What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

QuickRecall - Zero-Dependency Memory Engine. 常用记忆优先出现。零依赖 AI 记忆引擎，纯 Node.js。/ Prioritizes frequently used memories. Zero deps.

Persistent memory engine for AI agents with semantic recall, hotness prioritization, importance weighting, time decay, and auto-compaction. Zero external dep...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.5release · observed May 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173bjpr98qcngds2npjsk01ah85y9vx:quickrecall

Install using `clawhub skill install s173bjpr98qcngds2npjsk01ah85y9vx:quickrecall` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/chen-feng123/quickrecall before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chen-feng123-quickrecall/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

75,255 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: memory-enhancement-engine
description: Persistent memory engine for AI agents with semantic recall, hotness prioritization, importance weighting, time decay, and auto-compaction. Zero external dependencies. Pure Node.js.
tags:
  - memory
  - persistent
  - semantic-search
  - hotness
  - recall
  - ai-agent
  - nodejs
features:
  - Hotness-prioritized recall
  - Semantic search (bigram + character overlap)
  - Importance weighting (0-2.0)
  - Exponential time decay
  - Auto-compaction and pruning
  - Zero external dependencies
  - Pure Node.js
---

# Memory Enhancement Engine

**记忆增加引擎** — Persistent memory engine with hotness-prioritized semantic recall.

Memories that are recalled more often appear first — not just keyword matches.

## Quick Start

```bash
# Node.js API
const { MemorySystem } = require('./memory-enhancement-engine/memory.js');
const mem = new MemorySystem();

# CLI tool (view / search / compact)
node memory-enhancement-engine/memo.cjs status
node memory-enhancement-engine/memo.cjs query "something to find"
```

## Core Usage

```javascript
const { MemorySystem } = require('./memory-enhancement-engine/memory.js');

// Create engine (stores to MEMORY_STORE.json automatically)
const mem = new MemorySystem({ decayHalfLifeHours: 2 });

// Write a memory
mem.add({
  content: "Paris is the capital of France.",
  importance: 1.5,
  metadata: { tags: ["geography", "fact"] }
});

// Semantic search
const results = mem.query("France capital");
console.log(results);

// Get recent memories
const recent = mem.recent(10);

// Compact old memories (summarize low-importance clusters)
mem.compact(5, 0.3);
```

## API

| Method | Description |
|--------|-------------|
| `add(content, importance, metadata)` | Write a memory |
| `retrieve(query, k)` | Semantic search (returns sorted by score) |
| `getRecent(n)` | Get N most recent memories |
| `remove(predicate)` | Remove memories matching predicate |
| `compact(groupSize, minImportance)` | Compact old memories into summaries |
| `getStatus()` | Get engine stats (count, size, etc.) |

## Scoring Formula

```
score = similarity × 0.5 + recency × 0.3 + hotness × 0.2
```

Where hotness = log(1 + access_count) × exp(-time_delta / 86400)

## Features

- **Hotness-Prioritized Recall** — Frequently accessed memories get boosted scores
- **Semantic Search** — Bigram overlap + character-level similarity
- **Importance Weighting** — 0.0 (trivial) to 2.0 (critical)
- **Time Decay** — Half-life configurable (default 2 hours)
- **Auto-Prune** — Beyond 1000 entries, least important are pruned
- **Auto-Compaction** — Merge low-importance groups into summaries
- **No Server Needed** — Direct Node.js require, stores to local JSON

## Installation

| Method | Command |
|--------|---------|
| Copy | Copy `memory.js` + `memo.cjs` to your project |
| ClawHub | `clawhub install memory-enhancement-engine` |

## File Structure

```
memory-enhancement-engine/
├── SKILL.md
├── memory.js            # Core engine
├

README.md

# 宙一记忆系统 v3 — 初始化说明

## 架构

本系统把封装技能中的记忆引擎能力**内化到工作区**。

```
memo-lib/
├── memory.js          ← 记忆引擎核心（从封装技能复制，适度精简）
├── MEMORY_STORE.json  ← 持久化存储文件（自动管理，不要手动编辑）
└── README.md          ← 本文件

scripts/
└── memo.cjs           ← CLI 工具：写入/检索/查询/压缩/状态
```

## 如何使用

### 写入一条记忆

```bash
node scripts/memo.cjs add "内容" [importance=1.0] [tag1,tag2]
```

### 检索记忆

```bash
node scripts/memo.cjs query "关键词" [k=5] [min_imp=0]
```

### 查看状态

```bash
node scripts/memo.cjs status
```

### 压缩旧记忆

```bash
node scripts/memo.cjs compact [group_size=5] [min_imp=0.5]
```

## 封装技能 vs 宙一记忆系统

封装技能（卖的产品）：
- 独立部署，接受外部请求
- x402 支付验证
- REST API 对外暴露
- 多租户隔离

宙一记忆系统（这里）：
- 本地文件持久化，直接读写
- 无支付、无网络依赖
- 在启动流程中自动调用（AGENTS.md）
- 只有我一个用户
- 但要完整保留：语义检索、权重、时间衰减、压缩能力

_meta.json

{
  "ownerId": "kn78b7srwrx8xth7a4wcnapxyh85z0ts",
  "slug": "quickrecall",
  "version": "1.0.5",
  "publishedAt": 1777896080725
}

references/API_SPEC.md

# Memory Enhancement Engine — API Specification

## `MemorySystem`

Core class with persistent storage to local JSON file.

### Constructor

```javascript
new MemorySystem(config)
```

**Parameters:**
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `decayHalfLifeHours` | number | 2 | Exponential decay half-life |
| `simWeight` | number | 0.6 | Semantic similarity weight |
| `recencyWeight` | number | 0.4 | Recency weight |
| `storePath` | string | auto | Path to MEMORY_STORE.json |

---

### Methods

#### `add(entry) -> string`
Write a new memory.

- **Input:** `{ content: string, importance?: number (0-2.0), metadata?: object }`
- **Output:** `memory_id` — unique 12-char hex hash
- **Errors:** Empty content → `Error`

#### `query(text, k=5) -> Array`
Semantic search.

- **Input:** `text` — search query string; `k` — max results (1-50)
- **Output:** `[{id, content, importance, score, metadata, created_at, accessed_at, hit_count}, ...]`
- **Scoring:** similarity × simWeight + recency × recencyWeight + hotness × 0.2

#### `recent(n=10) -> Array`
Get N most recently created memories.

#### `get(id) -> object|null`
Get a single memory by ID. Increments hit_count.

#### `delete(id) -> boolean`
Delete memory by ID. Returns true if existed.

#### `compact(groupSize=5, minImportance=0.5) -> Array`
Compact low-importance memories into summaries.

- Groups oldest unaccessed memories, merges their content
- Returns compaction report: `[{group, summary, importance, original_ids}]`

#### `status() -> object`
Engine stats:
```json
{
  "count": 78,
  "storeSize": 30536,
  "decayHalfLifeHours": 2,
  "totalCompactions": 3
}
```

references/USE_GUIDE.md

# Memory Enhancement Engine — Usage Guide

## Installation

### Method 1: Copy files
```bash
# Copy to your project
cp -r memory-enhancement-engine ./my-project/
```

### Method 2: ClawHub
```bash
clawhub install memory-enhancement-engine
```

## Quick Start

### Basic Usage

```javascript
const { MemorySystem } = require('./memory-enhancement-engine/memory.js');

// Initialize
const mem = new MemorySystem();

// Store memories
mem.add({ content: "User prefers dark theme", importance: 1.5 });
mem.add({ content: "Billing is on the 15th of each month", importance: 1.2 });

// Search
const results = mem.query("dark mode preference");
console.log(results[0].content); // "User prefers dark theme"
console.log(results[0].score);   // 0.87 (example)

// Check status
const stats = mem.status();
console.log(`Memories stored: ${stats.count}`);
```

### CLI Tool

```bash
# View status
node memo.cjs status

# Search memories
node memo.cjs query "dark theme"

# View recent
node memo.cjs recent

# Compact old memories
node memo.cjs compact 5 0.3
```

### With Metadata

```javascript
mem.add({
  content: "Database connection string format",
  importance: 0.8,
  metadata: {
    tags: ["technical", "config"],
    source: "documentation",
    category: "backend"
  }
});

// Search with metadata context
const results = mem.query("database config");
```

## Best Practices

1. **Importance Levels** — Use 1.5+ for critical facts, 0.5-1.0 for normal info, 0.3 for ephemeral
2. **Compaction** — Run `compact()` periodically to keep memory lean (suggested: every 500 writes)
3. **Backup** — `MEMORY_STORE.json` is your persistence file; back it up regularly
4. **Capacity** — Default max 1000, adjust via constructor if needed

## Test

```bash
# Run test client
node scripts/test-client.js
```

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular