Mac Mini AI Server Monitoring: Keep Your Agent Running 24/7

<!-- ~/Library/LaunchAgents/com.myagent.server.plist -->
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"
  "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
  <key>Label</key>
  <string>com.myagent.server</string>

  <key>ProgramArguments</key>
  <array>
    <string>/path/to/bun</string>
    <string>run</string>
    <string>/Users/you/my-agent/src/cli.ts</string>
    <string>server</string>
  </array>

  <key>WorkingDirectory</key>
  <string>/Users/you/my-agent</string>

  <key>EnvironmentVariables</key>
  <dict>
    <key>PATH</key>
    <string>/usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin</string>
    <key>NODE_ENV</key>
    <string>production</string>
  </dict>

  <!-- Auto-restart on crash -->
  <key>KeepAlive</key>
  <dict>
    <key>Crashed</key>
    <true/>
  </dict>

  <!-- Throttle restarts to avoid rapid loops -->
  <key>ThrottleInterval</key>
  <integer>10</integer>

  <!-- Log output -->
  <key>StandardOutPath</key>
  <string>/Users/you/my-agent/.monitor/server.log</string>
  <key>StandardErrorPath</key>
  <string>/Users/you/my-agent/.monitor/server.log</string>

  <!-- Start at login -->
  <key>RunAtLoad</key>
  <true/>
</dict>
</plist>

launchctl load ~/Library/LaunchAgents/com.myagent.server.plist
launchctl start com.myagent.server

# Verify it's running
launchctl list | grep myagent

launchctl kickstart -k "gui/$(id -u)/com.myagent.server"

#!/bin/bash
# health-monitor.sh — runs every 5 minutes via cron

SERVER_URL="http://localhost:YOUR_PORT"
AUTH_TOKEN="your-auth-token"
LOG_FILE="$HOME/ai-server/.monitor/health-monitor.log"
ALERTS_FILE="$HOME/ai-server/.monitor/alerts.jsonl"
TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)

# Check server HTTP health
SERVER_STATUS="fail"
if curl -sf -H "Authorization: Bearer $AUTH_TOKEN"     "$SERVER_URL/health" --connect-timeout 5 --max-time 10     > /dev/null 2>&1; then
  SERVER_STATUS="ok"
fi

# Check Ollama
OLLAMA_STATUS="fail"
if curl -sf http://localhost:11434/api/tags     --connect-timeout 3 --max-time 8 > /dev/null 2>&1; then
  OLLAMA_STATUS="ok"
fi

# Check disk (alert if > 80%)
DISK_PCT=$(df -h / | awk 'NR==2 {gsub(/%/,"",$5); print $5}')
DISK_STATUS="ok:${DISK_PCT}%"
[ "$DISK_PCT" -gt 80 ] && DISK_STATUS="warn:${DISK_PCT}%"

# Check memory (free pages × 16KB)
FREE_PAGES=$(vm_stat | awk '/Pages free/{gsub(/./,"",$3); print $3}')
FREE_MB=$(( FREE_PAGES * 16384 / 1048576 ))
MEM_STATUS="ok:${FREE_MB}MB"
[ "$FREE_MB" -lt 4096 ] && MEM_STATUS="warn:${FREE_MB}MB"

# Log the check
echo "[$TIMESTAMP] Check: server=$SERVER_STATUS ollama=$OLLAMA_STATUS disk=$DISK_STATUS mem=$MEM_STATUS"   >> "$LOG_FILE"

# Auto-restart if server is down
if [ "$SERVER_STATUS" = "fail" ]; then
  echo "{"ts":"$TIMESTAMP","severity":"critical","message":"Server down — attempting restart"}"     >> "$ALERTS_FILE"

  launchctl kickstart -k "gui/$(id -u)/com.myagent.server" 2>/dev/null || {
    # Fallback: kill and restart
    lsof -ti:3000 | xargs kill 2>/dev/null
    sleep 2
    nohup bun run ~/ai-server/src/cli.ts server > ~/ai-server/.monitor/server.log 2>&1 &
  }

  sleep 15
  if curl -sf "$SERVER_URL/health" > /dev/null 2>&1; then
    echo "{"ts":"$TIMESTAMP","severity":"info","message":"Server restarted successfully"}"       >> "$ALERTS_FILE"
  fi
fi

*/5 * * * * /Users/you/my-agent/scripts/health-monitor.sh

#!/bin/bash
# log-watcher.sh — tails server log, emits structured alerts

LOG_FILE="$HOME/ai-server/.monitor/server.log"
ALERTS_FILE="$HOME/ai-server/.monitor/alerts.jsonl"

# Wait for log to exist
while [ ! -f "$LOG_FILE" ]; do sleep 5; done

tail -F "$LOG_FILE" | while read -r line; do
  TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)

  case "$line" in
    *"ENOMEM"*|*"out of memory"*)
      echo "{"ts":"$TIMESTAMP","severity":"critical","message":"OOM: $line"}" >> "$ALERTS_FILE"
      ;;
    *"EADDRINUSE"*|*"address already in use"*)
      echo "{"ts":"$TIMESTAMP","severity":"error","message":"Port conflict: $line"}" >> "$ALERTS_FILE"
      ;;
    *"Embedding API error"*|*"Failed to embed"*)
      echo "{"ts":"$TIMESTAMP","severity":"warning","source":"log-watcher","message":"$line"}" >> "$ALERTS_FILE"
      ;;
    *"SIGKILL"*|*"process dead"*)
      echo "{"ts":"$TIMESTAMP","severity":"critical","message":"Process killed: $line"}" >> "$ALERTS_FILE"
      ;;
  esac
done