Roadmap
The memory layer, in five phases.
rMem is a memory-layer platform. Today, MemoryPort handles import, search, and export. Each phase below adds a new capability to the same Postgres-backed memory store.
Phase 0 — MemoryPort
In progressImport, search, and export AI conversations across providers. Core flows shipped; billing (Stripe checkout, customer portal, plan reconciliation) still outstanding before Phase 0 closes.
IssuesSWR-36SWR-23SWR-24SWR-70SWR-71Phase 1 — Semantic retrieval
In progresspgvector embeddings, hybrid full-text + vector ranking, contextual chunk summaries.
IssuesSWR-76SWR-77SWR-78SWR-79SWR-85SWR-88Phase 2 — Memory API + MCP
PlannedREST API and MCP server (stdio + HTTP) so any agent can read and write memory.
IssuesSWR-80SWR-81SWR-82SWR-83SWR-84SWR-86Phase 3 — Structured memory
PlannedEntity extraction, dedup, memory management dashboard.
IssuesSWR-87SWR-89SWR-93Phase 4 — Temporal & graph intelligence
PlannedEntity relationship graph, GraphRAG queries, temporal facts and decay.
IssuesSWR-90SWR-91SWR-92
Issue identifiers reference internal Linear tickets. They are not deep-linked because the project is private.