brainwires-eval
cargoEvaluation harness for the Brainwires Agent Framework — fixtures, regression suites, stability tests, adversarial cases, ranking metrics (NDCG / MRR / precision@k), recorder.
Audits
No audits for this package yet.
Evaluation harness for the Brainwires Agent Framework — fixtures, regression suites, stability tests, adversarial cases, ranking metrics (NDCG / MRR / precision@k), recorder.