lossless-memory vs MemMolt
Lossless long-term memory for a personal AI: verbatim JSONL logs, time-first search over SQLite FTS5 (sqlite-vec as last resort) and a tiny 'where are we now' index injected every turn. — versus — 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.
Both are single-machine SQLite memory stores with FTS5 plus vector fallback; memmolt imposes a bucket-thread-memo hierarchy, lossless-memory keeps raw lines on a time axis.
| lossless-memory | MemMolt | |
|---|---|---|
| Stars | 143 | 4 |
| Forks | 13 | 0 |
| Language | Python | JavaScript |
| License | MIT | MIT |
| Last activity | 18 days ago | 6 months ago |
| Topics | memory | memory |
| Curated connections | 3 | 8 |
lossless-memory — the curator's take
Choose it for one person, one assistant, one machine, when 'what exactly did we say last Tuesday' matters more than distilled facts — it never summarizes, and time phrases narrow the range before anything is ranked. Not for multi-user products, agent fleets or benchmark-chasing: no server, no published evals. If you want extracted facts, profiles and forgetting, supermemory is the opposite philosophy.
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.