QMD Memory — 技能 — openclaw中文资讯站

技能详情（站内镜像，无评论）

Enables local hybrid memory search and embedding using QMD to reduce API costs by $50-300/month with automatic setup, smart indexing, and multi-agent sharing.

开发与 DevOps

许可证：MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本：v1.0.0

统计：⭐ 1 · 391 · 9 current installs · 9 all-time installs

⭐ 1

安装量（当前） 9

🛡 VirusTotal ：可疑 · OpenClaw ：可疑

Package：asabovetech/qmd-memory

安全扫描（ClawHub）

VirusTotal ：可疑
OpenClaw ：可疑

OpenClaw 评估

The skill mostly does what its description promises (local QMD-based memory), but there are a few inconsistencies and privacy/installation risks you should understand before installing.

目的

The skill's name/description (local QMD memory to reduce API spend) aligns with the included scripts and SKILL.md: setup installs QMD via npm, creates collections from your workspace, runs qmd update/embed, and can start an MCP server. However skill.json references a script (scripts/add-collection.sh) that is not present in the file manifest — this is an incoherence. The skill also declares no required env vars but relies on OPENCLAW_WORKSPACE…

说明范围

SKILL.md and scripts scan and index files under your workspace (default ~/.openclaw/workspace or OPENCLAW_WORKSPACE). Indexing 'workspace' is expected for a memory tool but can capture sensitive files (agent config, tokens, snippets containing credentials). The setup script will add collections for any matching directories and runs qmd embed (which processes local files). SKILL.md also shows a cron example for nightly updates, but the scripts …

安装机制

There is no package-level install spec; instead the setup script runs 'npm install -g @tobilu/qmd' at runtime. Installing a global npm package is common but downloads and runs third-party code (and that package will perform model downloads). The models (~2GB) are auto-downloaded by QMD from unspecified hosts. This is a moderate install risk because network downloads occur at setup time and code is fetched from the npm registry rather than a pi…

证书

The skill declares no required env vars or credentials, which is appropriate, but the setup script reads OPENCLAW_WORKSPACE (undeclared) and will scan that path and create collections. That means the skill may read and index any files under your workspace (including secrets stored in docs or config). It does not request external API keys (good), but the behavior of indexing arbitrary workspace files is a privacy risk and should be intentional …

持久

always:false and default autonomous invocation are normal. The skill does not request permanent platform-level privileges or modify other skills. It can start a local MCP HTTP server (qmd mcp --http --daemon) which may accept connections; the script claims localhost:8181 but does not explicitly bind/address-check. The skill also writes to ~/.cache/qmd (models, index, pid) — expected for a local search tool.

安装（复制给龙虾 AI）

将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「QMD Memory」。简介：Enables local hybrid memory search and embedding using QMD to reduce API costs …。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/asabovetech/qmd-memory/SKILL.md
（来源：yingzhi8.cn 技能库）

SKILL.md

打开原始 SKILL.md（GitHub raw）

# 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:
- `memory_search` → routes to QMD hybrid search
- `memory_get` → retrieves from QMD collections
- Results include collection context

### 5. Multi-Agent MCP Server (Optional)

```bash
# Start shared memory server
openclaw skill run qmd-memory serve

# All your agents can now query collective memory
# Forge, Thoth, Axis — shared knowledge base
```

---

## 📊 SEARCH MODES

| Mode | Command | Best For |
|------|---------|----------|
| **Keyword** | `qmd search "query"` | Exact matches, fast |
| **Semantic** | `qmd vsearch "query"` | Conceptual similarity |
| **Hybrid** | `qmd query "query"` | Best quality (recommended) |

### Example Queries

```bash
# Find exact mentions
qmd search "Charlene" -n 5

# Find conceptually related content
qmd vsearch "how should we handle customer complaints"

# Best quality — expansion + reranking
qmd query "what decisions did we make about pricing strategy"

# Search specific collection
qmd search "API keys" -c workspace
```

---

## 🔧 CONFIGURATION

### Add Custom Collections

```bash
openclaw skill run qmd-memory add-collection ~/Documents/research --name research
```

### Add Context

```bash
openclaw skill run qmd-memory add-context qmd://research "Market research and competitive analysis"
```

### Refresh Index

```bash
openclaw skill run qmd-memory refresh
```

---

## 💡 TEMPLATES

### Trading/Investing Workspace

```bash
openclaw skill run qmd-memory template trading
```

Creates:
- `intelligence` — Trading systems, dashboards, signals
- `market-data` — Price history, analysis
- `research` — Due diligence, reports
- `daily-logs` — Trade journal

### Content Creator Workspace

```bash
openclaw skill run qmd-memory template content
```

Creates:
- `articles` — Published content
- `drafts` — Work in progress
- `research` — Source material
- `ideas` — Brainstorms, notes

### Developer Workspace

```bash
openclaw skill run qmd-memory template developer
```

Creates:
- `docs` — Documentation
- `notes` — Technical notes
- `decisions` — ADRs, architecture decisions
- `snippets` — Code snippets, examples

---

## 📈 COST SAVINGS CALCULATOR

Run this to see your estimated savings:

```bash
openclaw skill run qmd-memory calculate-savings
```

Output:
```
Your Current API Memory Costs (estimated):
  memory_search calls/day:     ~75
  Average cost per call:       $0.03
  Monthly API cost:            $67.50

With QMD Local:
  Monthly cost:                $0.00

YOUR MONTHLY SAVINGS:          $67.50
YOUR ANNUAL SAVINGS:           $810.00

ROI on skill purchase:         40x (if skill was $20)
```

---

## 🛠️ TECHNICAL DETAILS

### Models Used (Auto-Downloaded)

| Model | Purpose | Size |
|-------|---------|------|
| embeddinggemma-300M-Q8_0 | Vector embeddings | ~300MB |
| qwen3-reranker-0.6b-q8_0 | Re-ranking results | ~640MB |
| qmd-query-expansion-1.7B-q4_k_m | Query expansion | ~1.1GB |

Total: ~2GB (one-time download)

### System Requirements

- Node.js >= 22
- ~3GB disk space (models + index)
- ~2GB RAM during embedding (then minimal)

### Where Data is Stored

```
~/.cache/qmd/
├── index.sqlite      # Search index
├── models/           # GGUF models
└── mcp.pid           # MCP server PID (if running)
```

---

## 🤝 SUPPORT

**Questions?** 
- GitHub Issues: github.com/asabove/qmd-memory-skill
- Discord: As Above community
- Email: support@asabove.tech

**Found it valuable?**
- Star us on ClawHub
- Share with other OpenClaw users
- Subscribe to our newsletter for more agent optimization tips

---

## 📜 LICENSE

MIT — Use freely, modify as needed.

QMD itself is created by Tobi Lütke (github.com/tobi/qmd).
This skill provides easy OpenClaw integration.

---

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

**As Above Technologies** — Agent Infrastructure for Humans