The bench compared mem0 with MindDB, FrameStore and HybridSearch from
the hive-mind substrate, which @waggle/core no longer exports and which
left the repository. It now runs mem0, mem0-rerank and cosine; the
recorded comparison stays in docs/oss/research/memory-search-quality.md.
Add a reference set (100 invented memories across personal memory and two
workspaces, 67 queries: paraphrase, keyword, multi-fact, scope, no-answer)
and a tsx benchmark that loads it into the old engine (MindDB, FrameStore,
HybridSearch, with and without the cross-encoder reranker), the mem0 store
and a plain-cosine baseline, all on Waggle's in-process embedder. It reports
recall@1, recall@5, MRR, latency and misses per engine and query type. The
mem0 half runs on its own (--engines mem0,cosine) once the old engine is
removed. Ollama and the user's own key are optional embedders; the bench
refuses network access to anything else and never reads OPENAI_API_KEY.
Results in docs/oss/research/memory-search-quality.md: mem0 matches the old
engine's chat-recall path (recall@1 0.72, recall@5 0.89 vs 0.90, MRR 0.82
vs 0.83) at a fraction of its latency and is acceptable for v1.
No new dependencies.
ADR-0007 maps today's memory usage onto the contract and mem0: profile
card and tasks move to waggle.db, learned facts stay in mem0, extraction
runs in the background in batches. Research notes cover what mem0 3.3.1
does and how 68 files use memory today. Two defects found on the way are
logged for the main project (UF-025, UF-026).