# Persistent storage and workspace memory (https://jackin.tailrocks.com/research/agents/orchestration/memory/)



**Research state:** Incomplete

**Verification cutoff:** 2026-08-12. Revalidate external storage and memory-system capabilities after this date.

## Research question [#research-question]

How should jackin❯ persist runtime events, account quota, task state, and cross-agent workspace memory while preserving isolation, provenance, lifecycle, and operator authority?

## Headline findings [#headline-findings]

* One structured storage layer avoids competing JSON files and gives status, GitHub, usage, tool, task, and memory consumers a consistent migration and retention model.
* Runtime state belongs in per-instance SQLite storage; provider account quota belongs in a daemon-global cache with one host-side writer.
* Workspace memory is distinct from packaged skills and prompts. It stores mutable preferences, project facts, workflow rules, review outcomes, and run summaries.
* Memory records need explicit scope, provenance, confidence, read/write policy, expiry, supersession, and access audit.
* Agents consume small runtime-neutral memory briefs through controlled adapters or MCP operations; they never open host storage directly.
* Per-instance and daemon-global databases require separate lifecycle and concurrency rules.

## Method and evidence [#method-and-evidence]

The design combines current jackin❯ runtime and telemetry needs with OpenMemory/Mem0, Letta shared blocks, Zep/Graphiti, runtime-native memory formats, multicode’s SQLite layout, and the workspace’s Turso storage constraint.

## Limitations and open questions [#limitations-and-open-questions]

* Choose the physical home for workspace memory so it survives instance purge without creating another authority.
* Document Turso production posture, migrations, multi-process behavior, and backup/export in an ADR.
* Validate explicit retrieval and operator curation before adding semantic indexes or external memory backends.
* Define which workflow-generated summaries and findings may append automatically.
* Keep durable operator preferences and project facts operator-controlled unless an accepted policy grants narrower write authority.

## How to read [#how-to-read]

1. [Memory requirements and prior art](/research/agents/orchestration/memory/01-requirements-and-prior-art/) establishes the product need and compares adjacent systems.
2. [Storage and memory data model](/research/agents/orchestration/memory/02-storage-and-memory-model/) defines tables, scopes, provenance, audit, and memory briefs.
3. [Delivery, lifecycle, and concurrency](/research/agents/orchestration/memory/03-delivery-lifecycle-and-concurrency/) defines APIs, global quota ownership, migrations, concurrency, trimming, and open policy.

## Related work [#related-work]

* [Agent Orchestration Program](/research/agents/orchestration/program-research/)
* [Token and cost telemetry](/research/agents/telemetry/token-cost-telemetry/)
* [GitHub link tracking](/roadmap/github-link-tracking/)
* [Autonomous task queue](/roadmap/autonomous-task-queue/)
* [Agent workflow orchestration](/research/agents/orchestration/workflow-systems/agent-workflow-orchestration/)
* [Native APM support](/research/agents/runtimes/package-manager-support/native-apm-role-support/)
* [Architecture Decision Records](/reference/adrs/)