タグ:confidence
confidence タグの付いた Jev GitHub プロジェクトを検索・並べ替えし、元のリポジトリを確認できます。
- 275jev-harnessDecision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.
AntonioCoppe/jev-harness · TypeScript
152ai-agentsconfidencedecisionevaluationharnessllm - 322jevelryUse Jev everywhere to make & track decisions
backant-io/jevelry · TypeScript
111agent-skillsclassificationclaude-codecodexconfidencecursordecision-model - 565tenbinMCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code
simota/tenbin · TypeScript
42agent-skillscalibrationclassificationclaude-codeconfidencellmmcp - 702calibreMeasure when to use Jev and other models on your data, then route accordingly.
FirasSX914/calibre · Python
20pythonbenchmarkcalibrationconfidence
4 件中 1–4 件