CLI for publishing and validating contract tests using judge-d API

Harness-backed AI testing on top of Vitest.

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

Render a deck JSON spec to a self-contained HTML slide deck.

Quadrat analysis lays a set of equal-size areas(quadrat) over the study area and counts the number of features in each quadrat and creates a frequency table.

No description provided.

Runtime asset loader and manifest for the WerewolfJudge web app — fonts, audio sprites, and image bundles

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

LLM-as-judge completion plugin for tagma-sdk pipelines

Rulvar evals: eval cases, golden outputs, rubric and judge graders, matrix sweeps, canary fingerprint.

Benchmark adapters and execution for agent-runtime across coding, tool-use, RAG, memory, browser, and terminal tasks.

Runtime type validation and assertion utilities

Copyright [@hydro-dev](https://github.com/hydro-dev) team.

looprun eval harness: run a generated subject's cases against a model target (governed or ungoverned variant), dump per-case traces for the LLM judge, fold verdicts, and certify against the bar.

Soul-bound workflow roles for Pi

:100: A set of utilities for judging programs on Exercode (https://exercode.willbooster.com/).

logrotator for egg

AI Coding Framework for Claude Code — 7+ agents, 52 skills, multi-LLM orchestration

Handsealed's deterministic trust rules: lanes, mandate binding, scope ceilings, evidence classes, verdicts.

It's a vue component that will count to a target number at a specified duration