QMD On-Device Search & Multi-Project Management SOP

# Register documentation and agent rules
qmd collection add /path/to/project/docs --name <proj>-docs
qmd collection add /path/to/project/.agents --name <proj>-agents

# Add human context summaries
qmd context add qmd://<proj>-docs "Technical documentation and architecture"
qmd context add qmd://<proj>-agents "AI constitution, palace brain, and skills"

# Generate embeddings
qmd embed

# Hybrid + Reranking search with collection scoping (recommended default)
qmd query "gitea podman setup" -c <proj>-docs

# Lexical BM25 search restricted to collection
qmd search "keyword" -c <proj>-docs

# Semantic vector search restricted to collection
qmd vsearch "conceptual description" -c <proj>-docs

# 1. Scan for new, modified, or deleted files across all collections (fast, ~1-2s):
qmd update

# 2. Embed only newly added/modified text chunks (skips all existing vectors):
qmd embed

# Optional: Clean up deleted file records & reclaim database space:
qmd cleanup

#!/usr/bin/env bash
# ==============================================================================
# QMD Hourly Incremental Sync Script (WSL2 / Linux)
# Protocol: Deep State of Mind (DSOM) v0.2
# ==============================================================================

set -euo pipefail

export PATH="$HOME/.npm-global/bin:$HOME/.local/bin:/usr/local/bin:/usr/bin:/bin:$PATH"
LOG_FILE="$HOME/.local/var/log/qmd-sync.log"

mkdir -p "$HOME/.local/var/log"
echo "[$(date '+%Y-%m-%d %H:%M:%S')] === Starting QMD incremental update ===" >> "$LOG_FILE"

if command -v qmd >/dev/null 2>&1; then
    qmd update >> "$LOG_FILE" 2>&1 || echo "[$(date '+%Y-%m-%d %H:%M:%S')] Warning: qmd update exited with code $?" >> "$LOG_FILE"
    qmd embed >> "$LOG_FILE" 2>&1 || echo "[$(date '+%Y-%m-%d %H:%M:%S')] Warning: qmd embed exited with code $?" >> "$LOG_FILE"
else
    echo "[$(date '+%Y-%m-%d %H:%M:%S')] ERROR: qmd binary not found in PATH" >> "$LOG_FILE"
    exit 1
fi

echo "[$(date '+%Y-%m-%d %H:%M:%S')] === QMD incremental update completed ===" >> "$LOG_FILE"

chmod +x ~/.local/bin/qmd-sync-hourly.sh
(crontab -l 2>/dev/null | grep -v "qmd-sync-hourly.sh" ; echo "0 * * * * /home/$USER/.local/bin/qmd-sync-hourly.sh") | crontab -

# Tool Signature in tools/mcp/server.py
qmd_search(query="gitea podman setup", collection="oss-docs", mode="query", limit=5)

{
  "mcpServers": {
    "qmd": {
      "command": "qmd",
      "args": ["mcp"]
    }
  }
}

# MASTER PROMPT: TURNKEY INTEGRATION OF QMD ON-DEVICE SEARCH

You are instructed to integrate the QMD (Query Markup Documents) local search engine into this project to enable AI agents and developers to execute fast local searches (BM25 + Semantic Vector Search + LLM Re-ranking) 100% on-device.

Please execute the following phases:

### PHASE 1: CHECK QMD AVAILABILITY
1. Check if the `qmd` binary exists:
   ```bash
   which qmd || which ~/.npm-global/bin/qmd

{
  "mcpServers": {
    "qmd": {
      "command": "qmd",
      "args": ["mcp"]
    }
  }
}

---
*Deep State of Mind (DSOM) For My AI Protocol | Harisfazillah Jamel (LinuxMalaysia) | 2026-10-09*
*Standard: UK English | DBP-standard Bahasa Melayu Malaysia (Piawai) | GNU General Public License v3.0*