deja-vu vs memanto
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 — Companion memory agent for 20+ coding agents, built on Moorcheh — its own information-theoretic engine, no third-party vector DB to manage. Runs local (Docker + Ollama, keyless) or on their cloud.
Both give coding agents cross-session memory with nothing to write by hand: deja-vu retro-indexes the logs your harnesses already produced (no hooks, no embeddings, months instantly), memanto runs its own retrieval engine over captured context. Instant history vs richer recall.
| deja-vu | memanto | |
|---|---|---|
| Stars | 688 | 1.8k |
| Forks | 55 | 626 |
| Language | Go | Python |
| License | MIT | MIT |
| Last activity | today | 3 days ago |
| Topics | memory, coding | memory, local |
| Curated connections | 4 | 5 |
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.
memanto — the curator's take
The no-third-party-infrastructure entry in the agent-memory category: retrieval runs on Moorcheh, the team's own information-theoretic engine, so there is no separate vector DB, embedding pipeline or reranker to manage — one CLI wires up 20+ agent integrations. Two deployments: fully local (Docker + Ollama, keyless, nothing leaves the machine) or their managed cloud (free tier, Moorcheh API key), which is also how shared team memory scales. The novel engine is the differentiator AND the risk: benchmark recall on YOUR corpus before trusting it over boring embeddings, and betting on Moorcheh is betting on one vendor's engine — memanto.ai signals the company behind it.