lossless-memory alternatives
Curated alternatives to lossless-memory — and why you'd switch.
MemMolt
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.
Why switchBoth 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.
Full comparison →deja-vu
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.
Why switchBoth recall verbatim history instead of LLM summaries; deja-vu indexes coding-agent session logs across 17 harnesses, lossless-memory one personal assistant's conversations.
Full comparison →supermemory
Memory and context engine for AI: fact extraction, user profiles, contradiction handling and forgetting, hybrid RAG + memory search, connectors, agent plugins and a one-binary local mode.
Why switchSame job — long-term memory for an assistant — opposite stance: supermemory extracts facts, builds profiles and forgets; lossless-memory never summarizes and returns the original lines with timestamps.
Full comparison →