Last released Oct 11, 2026
Unified LLM evaluation: A/B uplift, Panel/Jury judges, Krippendorff α, Cohen κ, pairwise preference, Elo tournament, and bias detection
Adversarial and red-teaming library: probe generation and attack methodologies for AI systems
Last released Sep 18, 2026
RETIRED — agent-wkp has moved to a Rust binary (wkp); see the project's GitHub Releases