conKurrence

nonedevelopment

AI evaluation toolkit â measure inter-rater agreement (Fleiss' Îº, Kendall's W) across multiple LLM providers

Install

How to run this server

[ { "cmd": "npx conkurrence", "imports": [] } ]

server path: conkurrence

Tools

What this server exposes

conkurrence_run

Execute an evaluation across multiple AI raters

conkurrence_report

Generate a detailed markdown report

conkurrence_compare

Side-by-side comparison of two runs

conkurrence_trend

Track agreement over multiple runs

conkurrence_suggest

AI-powered schema suggestion from your data

conkurrence_validate_schema

Validate a schema before running

conkurrence_estimate

Estimate cost and token usage

Configuration

Environment & auth

authnone

Resources