StackMap
Subscribe

MemMolt vs Memoria

Structured long-term memory over MCP: an enforced bucket-thread-memo hierarchy in one SQLite file, hybrid FTS5 + vector search fused with RRF, local embeddings. — versus — Rust memory layer for AI agents with Git-style version control — snapshot, branch, merge and rollback over MatrixOne's copy-on-write engine, plus hybrid vector + full-text retrieval.

The curated verdict

Both expose structured long-term memory over MCP; memmolt enforces a bucket-thread-memo hierarchy in SQLite, Memoria is a versioned memory database on MatrixOne.

MemMoltMemoria
Stars4422
Forks053
LanguageJavaScriptRust
LicenseMITApache-2.0
Last activity3 months ago27 days ago
Topicsmemorymemory
Curated connections54

MemMolt — the curator's take

The anti-sprawl memory play: a forced 3-level hierarchy the agent can't turn into a jungle, with ~10ms hybrid search from a single SQLite file and zero cloud calls. Young and tiny (4 stars) — the schema idea is worth studying even if you don't adopt it. Skip if you want auto-capture; this is deliberate, curated memory.

Memoria — the curator's take

Pick it when memory auditability and reversibility matter — you want to branch an agent's memory, roll back a bad write, or trace the provenance of every fact, and you're fine running MatrixOne underneath. Overkill if you just need a simple recall store (memmachine, memmolt) or fully-local files (memanto) — the versioning engine and DB dependency are the cost. Young project, Apache-2.0.