Temporal / graph agent memory
Agents must recall entities, relationships, and time-evolving facts — not just similar chunks.
At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/temporal-graph-memory#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
- Zep · 7.43/10 for this job (curated estimate, high confidence)
Capability of temporal graph memory over raw vector recall.
- Runner-up
- Mem0 · 7.58/10
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
- Simple preference/memory snippets — Mem0; pure vector RAG — Qdrant/pgvector.
- Lock-in / migration
- Runner-up Mem0 has lower stored lock-in risk (5 vs 5.2, 0–10, higher = more lock-in). Pick exit signals: open source (provider tag `oss`).
- 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
- No free resource lists this job. A cheap paid SKU is not a free option.
- Failure modes to watch
- Context overflow: If the input exceeds the window, say so and retrieve a narrower slice. Do not answer from a truncated head as if it were the whole source.
- 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 temporal-graph-memory: zep, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=temporal-graph-memory
Zep
Capability of temporal graph memory over raw vector recall.
Pricing (directional): As of 2026-10-24 (getzep.com/pricing, fetched 2026-10-24): Temporal knowledge-graph memory (Graphiti). 'Self-serve plans are credit based.' Free: 'Start free with 10,000 credits a month.' ('No rollover or auto-topup.'). Flex '$125 / month b…
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Pick when agents need temporal/entity graph memory, not just vector snippets. Mem0 for simpler recall.
Quote for Temporal / graph agent memory
Depot Pick stays Zep. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=temporal-graph-memory
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 5 candidates have no sourced price row. 5 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
Mem0
Default hosted agent memory bolt-on. Model retrieval volume carefully; self-host OSS if caps hurt.
Weaviate
Best when hybrid search and modularity matter. Cloud for convenience; self-host when lock-in anxiety spikes.
Letta Cloud
Choose when the agent IS a long-lived stateful runtime. For bolt-on memory use Mem0/Zep.
Cognee
Graph memory when documents→ontology matter. Zep for temporal bipartite graphs; Mem0 for simplest hosted…
When NOT to use the top pick
Simple preference/memory snippets — Mem0; pure vector RAG — Qdrant/pgvector.
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 | Weaviate | 8.2 | 8.8 | 7.5 | 8.4 | 8.2 | 2026-09-14 |
| 2 | Cognee | 8.1 | 8.4 | 8.8 | 7.6 | 8.2 | 2026-09-14 |
| 3 | Mem0 | 7.6 | 7.8 | 8.0 | 7.4 | 8.8 | 2026-09-14 |
| 4 | ZepDepot Pick | 7.4 | 8.2 | 7.0 | 7.6 | 7.8 | 2026-09-14 |
| 5 | Letta Cloud | 7.4 | 8.0 | 7.8 | 7.2 | 8.0 | 2026-09-14 |
Score methodology for this job
Capability of temporal graph memory over raw vector recall.
capabilityFit: 24%pricePerformance: 18%latencyReliability: 18%developerDx: 16%privacyPosture: 10%lockInRisk: 8%maturity: 6%