Skip to content
Back to skills

Claudiodrews Memory Os

ASecurity

Hệ thống bộ nhớ 7 lớp chạy local dành cho AI agent — SQLite + Qdrant + Fabric, zero cloud dependency. Agent nhớ project, decision, reasoning pattern xuyên session.

  • 10 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 9, 2026
ai-agentspythonrustbashsqldockergitapidatabase

Works with

  • api

Security analysis

A96/100
  • mediumUses curl or wget to download content

Pro shows the line behind each finding and how to fix it

Scanned September 9, 2026

npx -y skills add yanacuti1121/Yana-AI --skill claudiodrews--memory-os --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claudiodrews Memory Os?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Claudiodrews  Memory Os
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yanacuti1121-claudiodrews-memory-os/badge)](https://www.skillsdirectory.com/skills/yanacuti1121-claudiodrews-memory-os)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: claudiodrews--memory-os
description: "Hệ thống bộ nhớ 7 lớp chạy local dành cho AI agent — SQLite + Qdrant + Fabric, zero cloud dependency. Agent nhớ project, decision, reasoning pattern xuyên session."
allowed-tools: Bash, Read, Write
user-invocable: true
---

Memory OS biến Hermes Agent (hoặc bất kỳ LLM agent nào) thành collaborator dài hạn: nhớ đủ thứ giữa các session mà không cần cloud, không vendor lock-in.

## 7 Lớp Kiến Trúc

```
Layer 1 — Workspace Files
  MEMORY.md, USER.md, CREATIVE.md inject vào system prompt mỗi turn

Layer 2 — Session History
  SQLite + FTS5 full-text search — archive toàn bộ conversation

Layer 3 — Structured Facts
  Entity resolution + trust scoring + auto feedback loop

Layer 4 — Fabric (Cross-Session Extraction)
  LLM-powered summarization, 16 tools: fabric_recall, fabric_write, fabric_brief

Layer 5 — Vector Database
  Qdrant 4096-dim cosine + BM25 sparse, fallback: hybrid→dense→lexical→SQLite
  Weekly decay scan + semantic dedup (cosine > 0.92)

Layer 6 — Auto-Curated Wiki
  Self-organizing knowledge vault: concepts, entities, comparisons → Qdrant

Layer 7 — Ground Truth Hierarchy
  SOUL.md + rulebook.md — injected memory = authoritative
  Ngăn agent re-discover context đã có → tiết kiệm token
```

## Install

```bash
# One-command setup — Docker orchestrate Qdrant + Redis + ARQ worker
curl -fsSL https://raw.githubusercontent.com/ClaudioDrews/memory-os/main/install.sh -o /tmp/memory-os-install.sh
# Inspect first: head -40 /tmp/memory-os-install.sh — then run if safe:
bash /tmp/memory-os-install.sh
```

## Core Tools (Fabric Layer)

```python
fabric_recall(query, n=5)     # semantic search memory
fabric_write(content, tags)   # lưu fact mới
fabric_brief(session_id)      # summarize session → store
```

## Tích Hợp

```python
# Compatible với bất kỳ LLM provider nào Hermes support
# OpenRouter, OpenAI, Anthropic, Ollama, local models

# Databases:
# state.db — session history
# memory_store.db — facts + HRR (hierarchical relation)
# Qdrant — semantic vectors
```

## So Với Alternatives

| Feature | Memory OS | mem0 | Zep | Letta |
|---------|-----------|------|-----|-------|
| Fully local | ✅ | ❌ | ❌ | ❌ |
| Ground Truth layer | ✅ | ❌ | ❌ | ❌ |
| Trust-scored facts | ✅ | ❌ | ✅ | ❌ |
| Self-curating wiki | ✅ | ❌ | ❌ | ❌ |
| No subscription | ✅ | ❌ | ❌ | ❌ |

## Layer 7 — Quan Trọng Nhất

Nếu không có Ground Truth ranking: agent bỏ qua injected context, gọi API tìm lại thứ đã có trong prompt → waste token + slow.
Layer 7 force agent treat injected memory là authoritative source.

## Source

https://github.com/ClaudioDrews/memory-os · MIT

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.