3-layer-memory

Create a three-layer memory system with knowledge graph, daily notes, and tacit memory.

1|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/AskTinNguyen/vesper-team-skills --skill 3-layer-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 3-layer-memory
Source: https://github.com/AskTinNguyen/vesper-team-skills/tree/main/3-layer-memory
Command: npx skills add https://github.com/AskTinNguyen/vesper-team-skills --skill 3-layer-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The Three-Layer Memory System solves the challenge of retaining long-term, structured knowledge across AI conversations by organizing memory into a knowledge graph, daily notes, and a tacit memory layer that evolve with use.

Core Features & Use Cases

  • Three-layer architecture: Knowledge Graph (entities), Daily Notes, and Tacit Memory for persistent context.
  • Automatic synthesis and manual updates: weekly synthesis with options for automation while preserving history.
  • Extensibility: scripts, references, and assets to customize workflows and templates.

Quick Start

Run the initialization script to set up the three-layer memory structure and seed an example entity.

Frequently Asked Questions about 3-layer-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retain long-term context across AI conversations using a knowledge graph?

A three-layer memory system solves long-term context retention by organizing data into a knowledge graph, daily notes, and tacit memory. It automatically extracts facts and evolves across AI conversations.

What's the best way to set up a self-updating memory graph for entity management?

Set up a self-updating memory graph by running an initialization script that creates a three-layer structure. This seeds example entities and parses YAML frontmatter to maintain current and previous fact states.

How does fact state management work with [current] and [was] in a memory system?

Fact state management parses YAML frontmatter in entity files to maintain [current] and [was] states. This preserves historical fact accuracy within the knowledge graph over time.

Can I automate weekly synthesis and fact extraction across notes?

Weekly synthesis is supported with optional automation. The system automatically extracts facts and performs syntheses across daily notes and the knowledge graph while preserving history.

Do I need any dependencies to maintain a three-layer memory graph?

No dependencies are required. The three-layer memory graph operates independently using scripts, references, and assets to customize workflows and templates for entity management.

When should I not use a tacit memory layer for knowledge context?

A tacit memory layer is not suited for short-term or ephemeral context needs. It is designed for long-term, structured knowledge retention requiring automatic fact extraction and weekly syntheses.