Embedded / object-store vector DB
Want local or object-storage-centric vectors without a heavy managed cluster.
At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/embedded-vector#briefScores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.
- Depot Pick
- LanceDB · 7.79/10 for this job (curated estimate, medium confidence)
pricePerf + DX for embedded; DuckDB for analytics-adjacent light vector.
- Runner-up
- Chroma · 7.88/10
Scores higher than the pick on: Price / performance, Developer & agent DX, Lock-in risk (higher = worse), Maturity / track record.
- When not to use the pick
- Need filtered multi-tenant production QPS — Qdrant/Pinecone.
- Lock-in / migration
- Runner-up Chroma has lower stored lock-in risk (2.5 vs 3.5, 0–10, higher = more lock-in). Pick exit signals: open source (provider tag `oss`). Self-host fallback listed for this job: Chroma, LanceDB, FAISS.
- Sourced price (no comparable unit)
Pick: no sourced price in this job's unit (no_sourced_price).
No cheapest SKU (no_comparable_unit_for_job). No price was invented.
- Free option
- Failure modes to watch
- Stale retrieval: Store the source URL and the time it was fetched. If a newer canonical page exists, or two stored sources disagree, do not answer from the older one.
Cite: Agent Provider Depot, Depot Pick for embedded-vector: lancedb, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=embedded-vector
Free Embedded / object-store vector DB options
LanceDB
pricePerf + DX for embedded; DuckDB for analytics-adjacent light vector.
Pricing (directional): As of 2026-09-14: Embedded + cloud vector DB on Lance format; excellent local/OSS DX and object-storage-friendly indexing. Cloud usage-based; OSS free. Popular as RAG/memory backend (e.g. with Cognee); not a hosted 'agent memory' product it…
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Great embedded/object-store vector layer. Pair with Mem0/Zep only if you need higher-level memory APIs.
Quote for Embedded / object-store vector DB
Depot Pick stays LanceDB. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=embedded-vector
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Sourced price unavailable for the Depot Pick. No row in the pricing index.
5 of 6 candidates have no sourced price row. 6 are excluded from the Matching price comparison (none). no comparable sourced unit for this job; chat input $/1M and other units were not borrowed
Runners-up
Chroma
Prototype on Chroma; graduate to Qdrant/pgvector/Pinecone before your corpus and QPS grow up.
Turbopuffer
When your vector bill scares you and much of the corpus is cold, Turbopuffer is the interesting answer.
DuckDB (vector/extensions)
Use for local analytics + light vector experiments. Production agent memory → pgvector/Qdrant/Mem0.
When NOT to use the top pick
Need filtered multi-tenant production QPS — Qdrant/Pinecone.
Full ranking (score table)
Ranked with this JTBD's weights. Scores are curated estimates unless marked otherwise. Agents: prefer /api/decide then this table for tie-breaks.
| # | Provider | Overall | Fit | $/perf | Latency | DX | As of |
|---|---|---|---|---|---|---|---|
| 1 | MotherDuck | 8.4 | 8.8 | 8.6 | 8.6 | 9.0 | 2026-10-19 |
| 2 | Turbopuffer | 8.2 | 8.6 | 9.4 | 8.2 | 8.5 | 2026-09-14 |
| 3 | Cognee | 8.1 | 8.4 | 8.8 | 7.6 | 8.2 | 2026-09-14 |
| 4 | DuckDB (vector/extensions) | 8.0 | 6.0 | 9.5 | 7.5 | 8.5 | 2026-09-14 |
| 5 | Chroma | 7.9 | 7.2 | 9.0 | 7.0 | 9.2 | 2026-09-14 |
| 6 | LanceDBDepot Pick | 7.8 | 7.8 | 8.8 | 7.2 | 8.2 | 2026-09-14 |
Score methodology for this job
pricePerf + DX for embedded; DuckDB for analytics-adjacent light vector.
capabilityFit: 24%pricePerformance: 18%latencyReliability: 18%developerDx: 16%privacyPosture: 10%lockInRisk: 8%maturity: 6%