Agent Memory 🧠
Full intelligence layer: vector memory + knowledge graph + structured database.
When to Use
- - Storing and recalling facts semantically ("remember that Abidi prefers...")
- Managing structured data: projects, contacts, tasks, bookmarks
- Setting up the brain stack after container rebuild
- Batch seeding memory with key facts
Usage
Memory Engine (Mem0 — vectors + graph)
CODEBLOCK0
Structured Database (SQLite)
CODEBLOCK1
Setup & Seeding
CODEBLOCK2
Architecture
- - Mem0 — Unified AI memory (auto fact extraction, dedup, multi-level recall)
- Qdrant — Vector database for semantic search
- Neo4j — Knowledge graph for entities & relationships
- SQLite — Structured data (projects, contacts, tasks, bookmarks)
- Langfuse — Observability tracing on all operations
Credits
Built by
M. Abidi |
agxntsix.ai
YouTube |
GitHub
Part of the
AgxntSix Skill Suite for OpenClaw agents.
📅 Need help setting up OpenClaw for your business? Book a free consultation
Agent Memory 🧠
完整的智能层：向量记忆 + 知识图谱 + 结构化数据库。
使用场景
- - 语义化存储和回忆事实（记住Abidi偏好...）
- 管理结构化数据：项目、联系人、任务、书签
- 容器重建后设置大脑堆栈
- 批量植入关键事实记忆
使用方法
记忆引擎（Mem0 — 向量 + 图谱）
bash
存储事实
python3 {baseDir}/scripts/memory_engine.py add Abidi的业务专注于语音AI
语义回忆
python3 {baseDir}/scripts/memory_engine.py search Abidi的业务是做什么的
列出所有记忆
python3 {baseDir}/scripts/memory_engine.py get-all
测试连接（Qdrant、Neo4j、Langfuse）
python3 {baseDir}/scripts/memory_engine.py test
结构化数据库（SQLite）
bash
列出数据表
python3 {baseDir}/scripts/structured_db.py tables
插入数据
python3 {baseDir}/scripts/structured_db.py insert projects {name:MyProject,status:active}
查询
python3 {baseDir}/scripts/structured_db.py query SELECT * FROM projects
设置与植入
bash
容器重建后安装Python依赖
bash {baseDir}/scripts/setup_brain.sh
批量植入关键事实
python3 {baseDir}/scripts/seed_mem0.py
架构
- - Mem0 — 统一AI记忆（自动事实提取、去重、多级召回）
- Qdrant — 用于语义搜索的向量数据库
- Neo4j — 用于实体与关系的知识图谱
- SQLite — 结构化数据（项目、联系人、任务、书签）
- Langfuse — 所有操作的可观测性追踪
致谢
由
M. Abidi 构建 |
agxntsix.ai
YouTube |
GitHub
属于 OpenClaw 代理的
AgxntSix 技能套件 的一部分。
📅 需要为您的业务设置 OpenClaw？ 预约免费咨询
