[SwellJoe]

Everybody builds one. And, then they usually figure out that making the model fill its context with a bunch of memories hurts performance more often than it helps.

[esafak]

That's why I always ask: got benchmarks?

[zaydmulani]

Yes — cargo run -p mnemo-bench. Ships with 12 benchmarks. Full retrieval pipeline is ~4ms on debug build. Numbers are in the README performance table.

[SwellJoe]

I don't care if it's fast, if it makes the model dumber by cluttering up context.