Monitoring

Keep your Mnemosyne deployment healthy with built-in metrics and health checks.

Health Endpoint

GET /health

{
"status": "healthy",
"version": "2.0.0",
"db_connected": true,
"db_size_mb": 12.5,
"working_count": 42,
"episodic_count": 128,
"semantic_count": 64,
"last_sleep_at": "2026-04-25T13:00:00Z",
"uptime_seconds": 86400,
}

Metrics Endpoint

GET /metrics

# Prometheus-compatible output
mnemosyne_working_memory_entries 42
mnemosyne_episodic_memory_entries 128
mnemosyne_semantic_memory_entries 64
mnemosyne_query_latency_ms{quantile="0.5"} 65
mnemosyne_query_latency_ms{quantile="0.99"} 180
mnemosyne_consolidation_last_run 1714060800
mnemosyne_db_size_bytes 13107200

Key Metrics

MetricTargetAlert If
Query latency p50<100ms>200ms
Query latency p99<500ms>1000ms
DB size<1GB>5GB
Working memory<80% max>95%
Last consolidation<2x interval>3x interval

Logging

Mnemosyne uses structured JSON logging:

{
"timestamp": "2026-04-25T14:30:00Z",
"level": "INFO",
"component": "retrieval",
"event": "query_completed",
"latency_ms": 65,
"results_count": 5,
"query": "user preferences",
}

Alerting Rules (Prometheus)

groups:
- name: mnemosyne
  rules:
    - alert: HighQueryLatency
      expr: mnemosyne_query_latency_ms{quantile="0.99"} > 500
      for: 5m
      annotations:
        summary: "Mnemosyne query latency is high"

    - alert: MemoryNotConsolidating
      expr: time() - mnemosyne_consolidation_last_run > 7200
      for: 10m
      annotations:
        summary: "Mnemosyne consolidation has stalled"

Related Pages

Performance Tuning
Optimize Mnemosyne performance: index tuning, query optimization, cache configuration, WAL mode sett...
Backups
Implement backup strategies for Mnemosyne: SQLite file snapshots, incremental backups, automated res...
Deployment Overview
Overview of Mnemosyne deployment options: Docker, Fly.io, systemd services, and cron jobs. Choose th...