ECP is a standardized interface for orchestrating, auditing, and enforcing authority limits in AI Agent evaluations. It moves evaluation from "brittle Python scripts" to a deterministic infrastructure protocol

8 stars 3 forks 8 watchers Python Apache License 2.0
evaluation-metrics evaluations llm-evaluation model-evaluation
1 Open Issue Need Help Last updated: Aug 20, 2026

Open Issues Need Help

View All on GitHub

ECP is a standardized interface for orchestrating, auditing, and enforcing authority limits in AI Agent evaluations. It moves evaluation from "brittle Python scripts" to a deterministic infrastructure protocol

Python
#evaluation-metrics#evaluations#llm-evaluation#model-evaluation