Stateful long-lived agent runtime
Need agents with editable memory blocks and long-lived identity, not just a chat API + DB.
At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/stateful-agent-runtime#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
- Letta Cloud · 7.41/10 for this job (curated estimate, medium confidence)
Runtime capability; Letta for memory-native agents, LangGraph/Temporal for orchestration.
- Runner-up
- LangGraph Platform / LangSmith Deploy · 7.46/10
Scores higher than the pick on: Capability fit, Latency / reliability, Developer & agent DX, Maturity / track record.
- When not to use the pick
- Stateless request/response agents — plain LLM API + Mem0.
- Lock-in / migration
- The pick has lower stored lock-in risk than runner-up LangGraph Platform / LangSmith Deploy (5.5 vs 7.2). 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.
- Identity confusion: Bind every tool call to a user or tenant id. Refuse the call if that id changed mid-task. For a public bot, the operator owns the words the bot shows.
- Instruction drift: Restate the stop condition in the trace. End the run when it is met. Review long traces for steps that do not serve the original task.
Cite: Agent Provider Depot, Depot Pick for stateful-agent-runtime: letta, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=stateful-agent-runtime
Letta Cloud
Runtime capability; Letta for memory-native agents, LangGraph/Temporal for orchestration.
Pricing (directional): As of 2026-09-14: Stateful agent runtime (ex-MemGPT). Free tier BYOK + limited agents; Pro ~$20/mo; API plan ~$20/mo + ~$0.10/active agent/mo + tool-exec ~$0.00015/s (secondary/roundup figures as stored then). As of 2026-10-25 https://www.l…
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Choose when the agent IS a long-lived stateful runtime. For bolt-on memory use Mem0/Zep.
Quote for Stateful long-lived agent runtime
Depot Pick stays Letta Cloud. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=stateful-agent-runtime
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
LangGraph Platform / LangSmith Deploy
Deploy here if your graphs already are LangGraph. Otherwise Inngest/Temporal + Langfuse to avoid stack…
Temporal Cloud
Default durable orchestration for serious long-running agents. Inngest/Trigger.dev for lighter DX.
Mem0
Default hosted agent memory bolt-on. Model retrieval volume carefully; self-host OSS if caps hurt.
When NOT to use the top pick
Stateless request/response agents — plain LLM API + Mem0.
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 | Restate | 8.2 | 8.6 | 7.8 | 8.8 | 8.4 | 2026-09-14 |
| 2 | Temporal Cloud | 8.0 | 9.0 | 6.8 | 9.2 | 7.2 | 2026-09-14 |
| 3 | Mem0 | 7.6 | 7.8 | 8.0 | 7.4 | 8.8 | 2026-09-14 |
| 4 | LangGraph Platform / LangSmith Deploy | 7.5 | 8.4 | 6.8 | 8.0 | 8.2 | 2026-09-14 |
| 5 | Letta CloudDepot Pick | 7.4 | 8.0 | 7.8 | 7.2 | 8.0 | 2026-09-14 |
Score methodology for this job
Runtime capability; Letta for memory-native agents, LangGraph/Temporal for orchestration.
capabilityFit: 26%pricePerformance: 16%latencyReliability: 16%developerDx: 18%privacyPosture: 10%lockInRisk: 8%maturity: 6%