claude-memory-optimizer

Files (11)

• README.md
• SKILL.md
• feedback-example.md · examples/
• memory-frontmatter-example.md · examples/
• project-example.md · examples/
• reference-example.md · examples/
• package.json
• memory-pua-task.js · scripts/
• memory-pua.js · scripts/
• refactor-memory.js · scripts/
• task-pua.js · scripts/

SKILL.md (first lines)

# Claude Memory Optimizer

Structured memory system for OpenClaw with 4-type classification, automated migration, and **PUA-style maintenance checklist** (inspired by tanweai/pua - 14.8k GitHub stars).

## When to Use

- Setting up memory for the first time in OpenClaw
- Migrating from unstructured `memory/*.md` to organized categories
- Improving memory recall with semantic frontmatter
- Implementing Claude Code-style memory architecture

## Features

- **4-Type Classification**: user, feedback, project, reference
- **Frontmatter Metadata**: structured name/description/type for semantic search
- **Auto-Migration**: one-command refactor of existing memory files
- **Log Mode**: optional append-only daily logs (KAIROS style)
- **PUA-Style Maintenance**: 7 iron rules checklist with pressure escalation (L0-L4)

## Quick Start

### Install

```bash
clawhub install claude-memory-optimizer
```

### Run Migration

```bash
node ~/.openclaw/skills/claude-memory-optimizer/scripts/refactor-memory.js
```

### Run PUA Maintenance Check

```bash
# Normal mode (L0 - 3 checks)
node ~/.openclaw/skills/claude-memory-optimizer/scripts/memory-pua.js

# Strict mode (L3 - full 7 checks)
node ~/.openclaw/skills/claude-memory-optimizer/scripts/memory-pua.js --mode strict

# Audit mode (L4 - emergency fix)
node ~/.openclaw/skills/claude-memory-optimizer/scripts/memory-pua.js --mode audit
```

### Verify

```bash
ls -la ~/.openclaw/workspace/memory/
cat ~/.openclaw/workspace/MEMORY.md
```

## Memory Types

| Type          | Purpose                               | Example                                       |
| ------------- | ------------------------------------- | --------------------------------------------- |
| **user**      | User role, preferences, skills        | "Data scientist, prefers concise replies"     |
| **feedback**  | Behavior corrections/confirmations    | "No trailing summaries — user can read diffs" |
| **project**   | Project context, decisions, deadlines | "Thesis deadline: 2026-06-01"                 |
| **reference** | External system pointers              | "Kaggle: https://kaggle.com/chenziong"        |

## Directory Structure

```
memory/
├── user/          # User information
├── feedback/      # Behavior guidance
├── project/       # Project context
├── reference/     # External references
└── logs/          # Append-only logs (optional)
    └── YYYY/
        └── MM/
            └── YYYY-MM-DD.md
```

## Memory File Format

Each memory file uses frontmatter metadata:

```markdown
---
name: Data Science Background
description: User is a data scientist focused on observability and LLMs
type: user
---

User studies at Beijing University of Technology & UCD, GPA 3.95/4.2.
Research: LLM, AI Agents, MCP.

**Skills:** Python, PyTorch, Transformers, NLP

**How to apply:** Use data science terminology, assume ML background.
```

## What NOT to Save

- Code patterns, architecture, file paths (derivable from codebase)
- Git history, recent changes (use `git log`)
- Debugging solutions (fix is in the code)
- Content already in CLAUDE.md
- Ephemeral task details (only useful in current session)

## Configuration

### OpenClaw Config

```json
{
  "agents": {
    "defaults": {
      "memorySearch": {
        "enabled": true,
        "provider": "local",
        "maxResults": 20,
        "minScore": 0.3
      },
      "compaction": {
        "memoryFlush": {

From Arry8/openclaw-edge, MIT.

More from Arry8/openclaw-edge