chimera memory-bench

Measure recall@k as memory grows — lexical vs paraphrase. Default (keyword search, no key needed) surfaces the honest ceiling: exact-token recall holds at scale, but paraphrase recall collapses. Pass ``--semantic`` to re-run with the embedding recall path and watch the paraphrase column lift — that delta is the whole point of M11b.

Options

--sizesstrdefault: '50,200,1000'
Comma-separated memory sizes to sweep.
--semanticboolean
Use embedding recall (needs an embeddings key) to measure the lift.