A persistent recall layer that gives every Arcanada agent memory across sessions. We benchmarked three candidates (Hindsight, Graphiti, Mem0) and selected Hindsight, then validated the Model Connector path: Claude Haiku is stable, the Cursor connector turned out unsuitable for structured output. Production deployment is pending — research foundation is solid, hardening is the next horizon.
Capabilities
- Cross-session memory retention per agent
- Semantic memory retrieval via embeddings
- Forgetting policies — TTL plus relevance decay
- Hindsight backend (winner of internal benchmark)
- Per-agent isolation, no cross-tenant bleed
- Tested integration path with Model Connector + OpenRouter
- Structured-output requirement documented (no Cursor/Claude CLI)
Current autonomy level
L1
Weakest link
Research phase — no production hardening yet. A known race condition in shared workspaces during parallel commits is something any production memory layer must defend against.
Roadmap to L3
- L1 → L2 — production deploy on arcana-db, /health endpoint, basic deploy reporting.
- L2 → L3 — full observability, schema-validated reads/writes, fallback to no-memory mode on outage so agents degrade gracefully instead of crashing.
- Verification gate — soak test: 1000 concurrent agent sessions for 72 h with zero memory cross-contamination.