The Online Judge System's judger core for Node.js version. (Windows only so far)

Multi-judge consensus strategies for LLM Judge Toolkit

Multi-turn conversation agent evaluator with LLM-as-judge scoring.

> commandline-tool to judge male or female from Japanease text.

Toggle-based watchdog judge plugin for the OpenCode TUI

Additive LLM-as-judge code-quality scorer for Agentgrader

MCP server that lets an LLM analyze, judge, and choose chess moves (Stockfish + Maia3 + Lichess)

Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance

Evaluation harness for Eidentic agents — scorers, LLM-as-judge, dataset management, CI pass-rate gate, and production trace promotion.

Contexer Check — CI drift detection: judge a PR diff against a team's approved decisions and post an advisory score.

A driving loop for coding agents: a judge decides, an agent executes, a proof settles it. Cost, deliverables and progress are derived from the traces — never declared.

judge the path is absolute path or relative path

Online judge for node

Atbash safety judge plugin for AutoGen-style multi-agent orchestration

A fast and secure judge engine for Scratch projects

MCP agent security proxy — multi-layer detection (L1 heuristics, L2 embeddings, L3 LLM judge)

Run, judge, and stress-test competitive programming solutions from one CLI.

Task-level router + orchestrator for pi-coding-agent: LLM Judge routes each turn to a fast execution tier or a smart judgment tier, with multi-model fallback chains, exponential-backoff failover, and cache-aware routing; complex tasks escalate to a Smart

A utility for assigning a numeric score to a password entered by a user to judge its strength.

Whitecircle.ai tools for judge-style evaluations and rubric scoring.