---
title: Hindsight (Semantic Memory)
category: systems
tags: [hindsight, memory, postgresql, embeddings, semantic-search]
created: "2026-07-24"
modified: "2026-07-24"
---

# Hindsight (Semantic Memory)

## Deployment
- **Namespace:** hindsight (K8s)
- **API:** LoadBalancer `10.0.30.208:9177` (**NICHT localhost**, NICHT .201 — dort sitzt seit Rebuild 2026-08-01 Grafana!)
- **Health:** `curl -s http://10.0.30.208:9177/health`
- **Port-Mapping:** Svc 9177 → Container 8888; NodePort-Fallback 31577 (jeder Node)
- **LB-IP-Drift-Warnung:** LB-IPs verschoben sich beim Rebuild 2026-08-01 (hindsight .201→.208). Bei Health-Failure IMMER zuerst `kubectl -n hindsight get svc hindsight-api` gegenprüfen, statt Referenz-IP zu vertrauen
- **Backend:** PostgreSQL + pgvector
- **Config:** `~/.hermes/hindsight/config.json` (api_url gesetzt)

## Components
| Component | Status |
|-----------|--------|
| hindsight-api | 1/1 Running |
| hindsight-postgres | 1/1 Running |
| Embedding Model | harrier-oss (via noris) |

## API Endpoints
- `GET /health` — Health check
- `POST /retain` — Store memory
- `POST /recall` — Semantic search
- `POST /reflect` — Synthesize answer across memories

## Best Practices
- **retain_every_n_turns: 2** — reduziert Duplikate
- Vor Batch-Retain: Health-Check, dann erst retain calls feuern
- Meta-Memory Cleanup Cron: 1st of Month 03:00 (3 Dedup Rounds, Archive >6 Monate)
- Decay & Importance Scoring: 1st of Month 03:30 (score=access×age_decay, archive score<0.15)
- User Drift Detection: Mondays 04:00 (compare 14d vs 90d baseline)
- Skill Health Check: Mondays 04:30 (scan 187 SKILL.md for issues)
- Nightly Dream Cycle + Weekly Insight Digest

## What NOT to store in Hindsight
- Temporäre Task-States (→ session_search / todo)
- Workflows (→ Skills)
- Credentials (→ 1Password)
- Duplikate von MEMORY.md

## Related Skills
- `hindsight` (hindsight category)
- `compound-learning` (software-development category)

## Related
- [[systems/rke2-kubernetes]]
- [[concepts/credential-policy]]