skills.rest
yoonhwan
yoonhwanCOMMUNITY
Explore all skills by this author →
GitHub

memory-system

Manage a 3-tier memory system with Obsidian and NotebookLM integration.

3|2|Updated Mar 13, 2026
Search Tags:#memory management#knowledge curation#daily notes#notebooklm#agent context#obsidian sync#note logging
One-click install
npx skills add https://github.com/yoonhwan/ai-feature-pack --skill memory-system-yoonhwan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-system
Source: https://github.com/yoonhwan/ai-feature-pack/tree/main/feature-pack/memory-system/skill
Command: npx skills add https://github.com/yoonhwan/ai-feature-pack --skill memory-system-yoonhwan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the common issue of AI agents losing critical context between sessions, retaining fragmented knowledge across disconnected tools, and struggling to maintain consistent long-term memory for ongoing projects and interactions.

Core Features & Use Cases

  • 3-Layer Memory Architecture: Organizes agent knowledge into workspace memory, Obsidian second-brain vault, and optional NotebookLM Q&A layer for scalable, structured context retention.
  • Automated Daily Logging: Automatically records time-ordered session activity, key decisions, issues, and lessons to dated daily notes, with auto-creation for missing note files.
  • Cross-Tool Sync: Bidirectionally links notes to Obsidian vault folders (Meetings, People, News-Links) and integrates with NotebookLM for source-based Q&A on accumulated project knowledge.
  • Privacy Guardrails: Enforces rules to prevent sensitive data like API keys and personal information from being logged to shared notes, and blocks loading private long-term memory in group chat contexts. Use case: For example, a developer working on multiple long-term projects can use this Skill to automatically log all session work to daily notes, curate key project milestones to a central long-term memory file, save relevant research links to their Obsidian vault, and query past project decisions via NotebookLM without manually searching through old notes.

Quick Start

Use the memory-system skill to log today's session activity to a new daily note and sync relevant research links to your Obsidian News-Links folder.

Frequently Asked Questions about memory-system

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

FAQPage Schema
How do I retain long-term context for AI agents across sessions?▼

You can retain long-term agent context using a 3-tier memory system that organizes knowledge into workspace memory, an Obsidian second-brain vault, and a NotebookLM Q&A layer to prevent loss of critical knowledge between interactions.

Can I sync agent daily notes with my Obsidian vault?▼

Yes, you can bidirectionally sync agent notes with Obsidian vault folders like Meetings, People, and News-Links, automatically logging time-ordered daily activity and auto-creating missing dated note files.

Does this memory management approach work with NotebookLM for project Q&A?▼

Yes, the memory system integrates with NotebookLM to provide source-based Q&A on accumulated project knowledge, allowing you to query past decisions and research without manually searching through old notes.

How do I prevent sensitive data from being logged to shared agent memory?▼

Privacy guardrails automatically enforce rules to prevent sensitive data like API keys and personal information from being logged to shared notes, and block loading private long-term memory in group chat contexts.

Do I need obsidian-cli and nlm CLI tools to use this agent memory system?▼

The memory system integrates with obsidian-cli and nlm CLI tools for note and notebook operations, requiring these dependencies to enable cross-tool synchronization and source-based Q&A capabilities.

What's the best way to organize agent knowledge for ongoing long-term projects?▼

The best approach is a 3-layer architecture that separates workspace memory for active sessions, curates key milestones into long-term memory files, and uses NotebookLM for querying accumulated project knowledge.

Related Skills

Explore More Education & Research Skills→
lvndrylvndry
47

obsidian

Automate Obsidian note creation, retrieval, and vault organization via obsidian-cli.

Community
Advanced
dawsonblockdawsonblock

memory-recall

Retrieve relevant long-term memories and return source-aware summaries.

Community
Advanced
asonasasonas
5

wrapup

Summarize daily work from Things3, conversation, and second-brain into an Obsidian daily note.

Community
Advanced
wilsonfaustinowilsonfaustino
2

wrap-up

Automate end-of-session knowledge capture with Obsidian notes and memory updates.

Community
Intermediate