deja-vu vs lossless-memory
Indexes the session histories your coding agents already wrote — 17 harnesses, months retroactive — and serves recall over MCP. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One Go binary. — versus — 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.
Both recall verbatim history instead of LLM summaries; deja-vu indexes coding-agent session logs across 17 harnesses, lossless-memory one personal assistant's conversations.
| deja-vu | lossless-memory | |
|---|---|---|
| Stars | 1.1k | 143 |
| Forks | 112 | 13 |
| Language | Go | Python |
| License | MIT | MIT |
| Last activity | 3 days ago | 18 days ago |
| Topics | memory, coding | memory |
| Curated connections | 9 | 3 |
deja-vu — the curator's take
The inversion is the insight: every memory tool starts empty and records forward; deja starts FULL from history already on disk, and the no-LLM/no-embedding design means ~1.5ms search, zero keys, zero cost. When NOT: it remembers what your agents did, not curated knowledge — there's no write path for distilled lessons; and its benchmark numbers are self-published, so the standing caution on this shelf applies: benchmark recall on your own corpus.
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.