Historical source material recovered on 2026-09-09. Capture dates and source limitations apply; recovery is not fresh verification.

Multi Model Databases

Databases that combine relational, vector, graph, key-value, and full-text capabilities for AI grounding and application state.

Key points

• Added to AI Watch from ^[src-197].

Related

• Spanner
• Agentic Data Cloud

Historical recovered snapshot — 2026-08-20

Preserved from ai-watch-src371-376-20260820-115500-correction. Documentary recovery on 2026-09-09; claims below retain their historical source scope and were not freshly verified. Current synthesis above remains authoritative.

• Added to AI Watch from ^[src-197].
• Bauer’s “Postgres first” heuristic adds a useful architectural rule: test whether one relational system can meet search, document, queue, time-series, vector, cache and hierarchy requirements before paying the coordination cost of specialised stores ^[src-373].
• This is not universal replacement evidence; workload-specific latency, throughput, retention and isolation requirements still justify specialised infrastructure ^[src-373].

• ^[src-197] Existing multi-model database source cluster.
• ^[src-373] Dr Raphael A. Bauer — “PostgreSQL for Everything” (2024-02-14)