Qmd Memory

# QMD Memory Skill for OpenClaw
## Local Hybrid Search — Save $50-300/month in API Costs

**Author:** As Above Technologies
**Version:** 1.0.0
**ClawHub:** [Coming Soon]

---

## 💰 THE VALUE PROPOSITION

### API Costs You're Paying Now

| Operation | API Cost | Frequency | Monthly Cost |
|-----------|----------|-----------|--------------|
| memory_search (embedding) | $0.02-0.05 | 50-200/day | $30-300 |
| Context retrieval | $0.01-0.03 | 100+/day | $30-90 |
| Semantic queries | $0.03-0.08 | 20-50/day | $18-120 |
| **TOTAL** | | | **$78-510/month** |

### With QMD Local

| Operation | Cost | Why |
|-----------|------|-----|
| All searches | **$0** | Runs on your machine |
| Embeddings | **$0** | Local GGUF models |
| Re-ranking | **$0** | Local LLM |

**Your savings: $50-300+/month**

One-time setup. Forever free searches.

---

## 🚀 QUICK START

```bash
# Install the skill
clawhub install asabove/qmd-memory

# Run setup (installs QMD, configures collections)
openclaw skill run qmd-memory setup

# That's it. Your memory is now supercharged.
```

---

## WHAT YOU GET

### 1. Automatic Collection Setup

Based on your workspace structure, we create optimized collections:

```
✓ workspace     — Core agent files (MEMORY.md, SOUL.md, etc.)
✓ daily-logs    — memory/*.md daily logs
✓ intelligence  — intelligence/*.md (if exists)
✓ projects      — projects/**/*.md (if exists)
✓ documents     — Any additional doc folders you specify
```

### 2. Smart Context Descriptions

We add context to each collection so QMD understands what's where:

```
qmd://workspace    → "Agent identity and configuration files"
qmd://daily-logs   → "Daily work logs and session history"
qmd://intelligence → "Analysis, research, and reference documents"
```

### 3. Pre-configured Cron Jobs

```bash
# Auto-update index (nightly at 3am)
0 3 * * * qmd update && qmd embed

# Keep your memory fresh without thinking about it
```

### 4. OpenClaw Integration

Memory search now uses QMD automatically:
- `memo...

# QMD Memory Skill for OpenClaw

## 💰 Save $50-300/month in API Costs

**Stop paying for memory. Start compounding knowledge.**

Every time your agent searches memory via API, you pay. With QMD Memory, all searches run locally — completely free, forever.

[![ClawHub](https://img.shields.io/badge/ClawHub-Install-blue)](https://clawhub.com/skills/asabove/qmd-memory)
[![License](https://img.shields.io/badge/License-MIT-green)](LICENSE)

---

## The Math

| Without QMD | With QMD |
|-------------|----------|
| 50-200 memory searches/day | Same searches |
| $0.02-0.05 per search | **$0 per search** |
| $30-300/month in API costs | **$0/month** |

**Annual savings: $360-3,600**

---

## Quick Start

```bash
# Install
clawhub install asabove/qmd-memory

# Setup (5-10 minutes, one time)
openclaw skill run qmd-memory setup

# Done. Your memory now costs $0.
```

---

## What You Get

✅ **Local hybrid search** — BM25 + vectors + LLM re-ranking  
✅ **Auto-configured collections** — Based on your workspace structure  
✅ **Smart context** — QMD understands what's in each collection  
✅ **Nightly auto-updates** — Index stays fresh automatically  
✅ **Multi-agent support** — Shared memory via MCP server  
✅ **Zero ongoing costs** — All models run locally  

---

## How It Works

QMD (by Tobi Lütke) combines three search technologies:

1. **BM25** — Fast keyword matching (SQLite FTS5)
2. **Vector Search** — Semantic similarity (local embeddings)
3. **LLM Re-ranking** — Quality filtering (local Qwen model)

This skill configures QMD for OpenClaw and integrates it with your agent's memory system.

---

## Commands

```bash
# Calculate your savings
openclaw skill run qmd-memory calculate-savings

# Search your memory
qmd query "what did we decide about pricing"

# Refresh index
openclaw skill run qmd-memory refresh

# Start shared server (for multi-agent)
openclaw skill run qmd-memory serve
```

---

## Templates

```bash
# For traders/investors
openclaw skill run qmd-memory te...