padosoft/eval-harness
What it is
A Laravel-native evaluation framework for RAG and LLM pipelines that uses golden datasets, LLM-as-judge metrics, and statistical regression detection. It operates entirely within the application via Artisan commands, allowing developers to measure, compare, and gate changes to their AI agents.
The problem it solves
Standard evaluation tools lack statistical rigor for detecting real changes in LLM outputs and do not natively integrate with Laravel's ecosystem or provide per-row regression tracking.
What you could use it for
- Regression testing for RAG pipelines in Laravel applications
- Evaluating agent tool-calling trajectories and step budgets
- CI/CD gating for LLM-based features using statistical confidence
- Generating actionable briefings from evaluation reports
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.