auraone-evalkit is an open-source Python CLI tool that helps AI researchers and developers evaluate models using standardized rubrics. It supports deterministic scoring, reviewer agreement analysis, drift detection, leakage audits, and generates comprehensive evaluation reports. The tool is designed for local use and is suitable for teams working on LLM and AI model validation.
Latest indexed changes and source events
auraone-evalkit discovered by the PulseGate indexer
Other apps tracked under the same category.
