Overview
- Skill Key
- guohongbin-git/memory-sync-enhanced
- Author
- guohongbin-git
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/guohongbin-git/memory-sync-enhanced
- Latest Commit SHA
- 85945715d10622d3169497fe7207c5aa990574d4
增强版记忆系统 - Ebbinghaus 遗忘曲线 + Hebbian 共现图
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 memory-sync-enhanced 技能。 若已安装,则直接安装 memory-sync-enhanced 技能。
# 增强版记忆系统
结合 **Ebbinghaus 遗忘曲线** + **Hebbian 共现图** 的双层记忆架构。
## 架构
```
┌─────────────────────────────────────────────────────────┐
│ 记忆检索 │
│ semantic_search() + co_occurrence_boost() + decay() │
└─────────────────────────────────────────────────────────┘
│
┌───────────────┴───────────────┐
▼ ▼
┌─────────────────────┐ ┌─────────────────────┐
│ Layer 1: 向量库 │ │ Layer 2: 共现图 │
│ (CortexGraph) │ │ (Hebbian) │
│ │ │ │
│ • 语义相似度 │◄─────►│ • 操作关联 │
│ • Ebbinghaus 衰减 │ │ • 边权重衰减 │
│ • use_count 追踪 │ │ • 跨域桥接 │
└─────────────────────┘ └─────────────────────┘
```
## 核心算法
### Layer 1: Ebbinghaus 遗忘曲线
```
score = (use_count)^β × e^(-λ × Δt) × strength
```
- **β** = 0.6(使用频率权重)
- **λ** = ln(2) / half_life(默认 3 天)
- **strength** = 1.0-2.0(重要性)
### Layer 2: Hebbian 共现图
```
effective_weight = weight × 2^(-age_days / 30)
```
- 每次记忆 A 和 B 同时被检索 → 边(A,B) 权重 +1
- 边权重 30 天半衰期
- **跨域桥接**:音乐记忆 ↔ 编码记忆(因为同时发生)
## 检索流程
```python
def retrieve_memory(query, top_k=10):
# 1. 语义搜索
semantic_results = cortexgraph.search(query, top_k * 2)
# 2. 共现增强
for mem in semantic_results:
co_occur_boost = get_co_occurrence_score(mem.id, recent_context)
mem.boosted_score = mem.semantic_score + co_occur_boost * 0.3
# 3. 遗忘曲线过滤
for mem in semantic_results:
mem.final_score = mem.boosted_score * mem.decay_factor
# 4. 返回 Top K
return sorted(semantic_results, key=lambda x: x.final_score)[:top_k]
```
## 记忆类型
### STM (短期记忆)
- JSONL 格式
- 快速读写
- 高衰减率(3天 half-life)
- 存储日常日志
### LTM (长期记忆)
- Obs...
# Memory Sync Enhanced 增强版记忆系统 - Ebbinghaus 遗忘曲线 + Hebbian 共现图。 ## 架构 ``` Layer 1: CortexGraph (语义搜索 + 遗忘曲线) Layer 2: Co-occurrence Graph (操作关联) ``` ## 核心概念 1. **Ebbinghaus 遗忘曲线** - 管理记忆生命周期 2. **Hebbian 共现图** - 记录记忆之间的关联 3. **双层检索** - 语义相似 + 操作相关 ## 使用 ```bash # 同步记忆 ./scripts/sync-memory.sh # 搜索记忆(增强版) python3 scripts/co_occurrence_tracker.py ``` ## 参考 - @Zeph 的 Hebbian 共现图帖子 (The Colony) - CortexGraph 遗忘曲线 ## 许可证 MIT
youmind-openlab
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
23blocks-os
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between computers and locations
hashgraph-online
AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.
rito-w
A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.
besoeasy
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, search, web scraping & more. No trial-and-error, no expensive APIs.
zeropointrepo
YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, ClawdBot, Claude Code, Cursor, Windsurf.