Skip to content

Eamon3949/Three-layer-memory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 Genius Three-Layer Memory System v3.0

The Ultimate Cognitive Architecture for AI Agents (Vector + Graph Engine)

Python 3.8+ ChromaDB NetworkX License: MIT

English | 中文说明


🇬🇧 English Version

Welcome to the Genius Three-Layer Memory System v3.0. This is not just another "scratchpad" or simple RAG plugin. It is a complete cognitive upgrade for AI Agents, moving away from fragile markdown files into a real-time, event-driven hybrid database architecture.

🌟 Why V3.0? The Paradigm Shift

  • Zero Amnesia: Instant vector embeddings ensure that every rule or event is internalized immediately.
  • Logical Reasoning: By building a Knowledge Graph, the AI understands causality and relationships, not just keywords.
  • Visual Mind Mapping: Generate a visual snapshot of the AI's current understanding with a single command.

🏗 Architecture

  1. L1: Working Memory: Handles immediate conversational flow.
  2. L2: Episodic Memory (ChromaDB): Stores conversational slices and rules as high-dimensional vectors.
  3. L3: Semantic Memory (NetworkX): A dynamic Knowledge Graph mapping entities and relationships.

🚀 Quick Start

1. Install Dependencies

pip install chromadb sentence-transformers networkx matplotlib

2. CLI Commands

  • Learn: python memory_v3.py learn "Rule" "Subject" "Object" "Relation"
  • Think: python memory_v3.py think "Query" "Target_Node"
  • Map: python memory_v3.py map

🇨🇳 中文版本

欢迎来到 Genius 天才三层记忆系统 v3.0。 这绝不是一个简单的"错题本",而是为全能型 AI Agent 打造的终极认知架构。我们彻底抛弃了脆弱的纯文本日志,全面拥抱实时驱动的"向量+图谱"双引擎。

🌟 为什么是 V3.0?架构降维打击

  • 拒绝记忆滞后:事件发生即刻向量化存入 ChromaDB,形成"肌肉记忆"。
  • 钢铁般的逻辑推理:引入 NetworkX 图数据库,AI 顺着节点理解"因果链"与"实体关系"。
  • 一图胜千言:只需一行指令,即可将 AI 认知关系网渲染为可视化拓扑图。

🏗 三层认知架构

  1. L1 短期工作记忆: 负责即时对话承接。
  2. L2 情景记忆库 (ChromaDB): 将有价值的规则转化为高维向量。
  3. L3 结构化图谱 (NetworkX): 沉淀核心规则、角色权限,构建知识大厦。

🚀 极速部署

1. 安装依赖

pip install chromadb sentence-transformers networkx matplotlib

2. 核心指令

  • 学习新规: python memory_v3.py learn "规则" "主体" "客体" "关系动作"
  • 主动唤醒: python memory_v3.py think "情景" "核心对象"
  • 生成脑图: python memory_v3.py map

Created by Eamon | Powered by OpenClaw Ecosystem

About

Genius 天才三层记忆系统

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages