Skip to content
Agentmart
Submit a tool

memory-system

3-tier hierarchical memory management for AI agents.

Skill by mupengi-bot

IndexedMIT★ 10
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mupengi-bot-memory-system

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

3-tier hierarchical memory management for AI agents. L1 (daily active context, ~100 lines), L2 (weekly decisions/insights, ~400 lines), L3 (long-term archive, unlimited). Includes self-improvement loop, session continuity, semantic search, and mistake-tracking. Use when starting a session (load memory), ending a session (save memory), during heartbeats (memory maintenance), or when explicitly asked to manage/organize/promote/clean memories.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/memory-system

What's inside

Skill name
memory-system
Description
3-tier hierarchical memory management for AI agents. L1 (daily active context, ~100 lines), L2 (weekly decisions/insights, ~400 lines), L3 (long-term archive, unlimited). Includes self-improvement loop, session continuity, semantic search, and mistake-tracking. Use when starting a session (load memory), ending a session (save memory), during heartbeats (memory maintenance), or when explicitly asked to manage/organize/promote/clean memories.
License
MIT
Instructions
285 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: references/mistake-template.md

Files (4)

  • SKILL.md
  • L1-template.md · references/
  • L2-template.md · references/
  • daily-template.md · references/

SKILL.md (first lines)

# Memory System v2 — 3-Tier Hierarchical Memory 🐧

> **통합:** agent-memory-kit의 자기 개선 + 세션 연속성 + 실수 추적 기능이 병합되었습니다.

## Architecture

| Tier | File | Purpose | Size Limit | Update Frequency |
|------|------|---------|-----------|-----------------|
| **L1** | `memory/L1-active.md` | Immediate working context | ~100 lines | Every session |
| **L2** | `memory/L2-weekly.md` | Weekly decisions & insights | ~400 lines | Weekly |
| **L3** | `MEMORY.md` | Permanent archive | Unlimited | As needed |

---

## L1 — Active Context

Current day's state. Load this first every session.

**Contains:** Today's events, active tasks, bot status, next actions, key values to remember.

**Rules:**
- Overwrite daily — yesterday's L1 becomes a daily file (`memory/YYYY-MM-DD.md`)
- Keep under 100 lines
- Structure: 핵심 사건 → 진행 중 → 핵심 가치관 → 다음 할 일

---

## L2 — Weekly Digest

Week's accumulated decisions and insights.

**Contains:** Key decisions made, weekly insights, project status snapshots, people updates.

**Rules:**
- Reset weekly (Sunday or Monday)
- Old L2 content promotes to L3 or gets archived as `memory/L2-week-YYYY-MM-DD.md`
- Keep under 400 lines
- Only include items with lasting relevance (>1 day lifespan)

---

## L3 — Long-term Archive (MEMORY.md)

Permanent knowledge base. Curated wisdom.

**Contains:** Core insights, 형님's teachings, identity principles, project histories, relationship notes.

**Rules:**
- Priority tagged: `[P1]` critical, `[P2]` important, `[P3]` reference
- Searchable tags: `<!-- [태그명] -->` for grep
- Remove outdated entries periodically
- Only promote items that passed the "will this matter in a month?" test

---

## Promotion Flow

```
Daily events → L1 (today)
                ↓ (end of day)
              memory/YYYY-MM-DD.md (archive)
                ↓ (significant items)
              L2 (weekly digest)
                ↓ (lasting insights)
              L3 (permanent)
```

### Promotion Criteria

**L1 → L2:** Decision that affects future work, insight worth remembering beyond today, relationship change, project milestone.

**L2 → L3:** Principle or value learned, identity-level insight, 형님's teaching, pattern that keeps recurring, critical project history.

---

## Session Lifecycle (v2 Enhanced)

### 🚀 Session Start Checklist (Auto-run)

Run this checklist **every session start** without asking:

1. **Read core files:**
   - `SOUL.md` — who you are
   - `SELF.md` — current self-description
   - `L1-active.md` — today's context
   - Today's + yesterday's daily logs (`memory/YYYY-MM-DD.md`)
   - **`MEMORY.md` — only in main session** (not in Discord/group chats)

2. **Context check:**
   - Any unfinished tasks from yesterday?
   - Any active issues/blockers?
   - Any upcoming deadlines?

3. **Mental state:**
   - Review last session's mistakes (if any) from `memory/mistakes/`
   - Check for recurring patterns

**No permission needed. Just do it.**

---

### 🛑 Session End Checklist (Auto-run)

Run this **every session end** without asking:

1. **Update L1:**
   - Write today's state to `L1-active.md`
   - Include: key decisions, active tasks, next actions

2. **Archive daily log:**
   - Save raw session log to `memory/YYYY-MM-DD.md`
   - Include: conversations, decisions, context

3. **Promote to L2 (if significant):**
   - If today had important decisions/insights, update `L2-weekly.md`

4. **Mistake tracking (if applicable):**
   - If you made a mistake today, log it to `memory/mistakes/YYYY-MM-DD-{topic}.md`
   - Include: what happened, why, how to prevent

From mupengi-bot/mupengism, MIT.

More from mupengi-bot/mupengism

Signals

Stars
10
Forks
2
Open issues
2
Last commit (this folder)
Feb 13, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mupengi-bot

Cite this page

memory-system skill. Agent Mart. https://agentmart.dev/skills/mupengi-bot-memory-system (last updated 2026-10-24)