LLM Evaluation Harness
Run evals as part of CI — measure LLM output quality on every change
5 packages · Health-checked and current
RolePackageHealthScoreAlternatives
Evaluation
Inactive
Hero Score 57
, ,
LLM Orchestration
Recently updated
Hero Score 77
,
Data Validation
Active
Hero Score 87
, , ,
Monitoring
Recently updated
Hero Score 79
, , ,
Testing
Recently updated
Hero Score 91
, , ,