Memory Health Probe
Telemetry for QMD memory systems. Measures index health, retrieval quality, and coverage to catch degradation before it affects agent performance.
Metrics Captured
- Index health — file count, chunk count, index size, staleness
- BM25 quality — hit rate + score distribution over canonical queries
- Gateway events — session-memory saves, QMD armed events
- Coverage map — which collections are hit for which query categories
Usage
python3 scripts/memory_probe.py # Run probe, log to Langfuse
python3 scripts/memory_probe.py --dry-run # Print results only
python3 scripts/memory_probe.py --trend # Show trend over stored snapshots
Files
scripts/memory_probe.py— Probe script with Langfuse integration