Maestro Frontier is an opt-in, zero-dependency local multi-CLI fusion engine for AI coding agents. Compose an Opus 5 and Codex model panel, set provider-supported effort, judge its one-shot read-only responses, and synthesize one grounded answer. Optional

Static HTML dashboard generator for judge-java

Evaluate AI-generated educational content with deterministic checks and LLM-as-judge scoring

LLM judge clients for slopstop Layer 2. Vendor-neutral, dependency-free (raw fetch).

LLM-as-judge for classifier evaluation with cost tracking

Run your smart-contract bug bounty finding through a strict 7-gate validity judge before you spend a submission on Sherlock, Immunefi or Cantina.

I think in normal cases, everyone just copies queries from graphiql. But this library creates programmatically generated queries, do not judge strictly =)

Multi-backend caching for LLM Judge Toolkit

Deterministic + semantic verification of quote-grounded LLM citations (EVI1 protocol): fuzzy verbatim-quote matching and an LLM entailment judge for transparent, per-claim hallucination detection.

MCP server for Inmigreat Pro — immigration case intelligence for attorneys. 17 tools: case management, judge analytics, AI predictions, legal precedent search, lead matching, client coaching, and more.

judge event inside component

Unified Online Judge information collector.

Scenario runner for software-factory specs — runs `test:` satisfaction lines and scores `judge:` lines via LLM

Splitifi Intelligence MCP — outcome predictions, judge profiles, and legal workflows powered by 29,211 production ML models trained on real court records. Serves litigants, attorneys, judges, mediators, CDFAs, and litigation funders.

An LLM safety judge in front of tool calls OMP would otherwise auto-approve. Hard-blocks clear attacks and clear mistakes, escalates genuine uncertainty to a human.

Multi-model AI consultation MCP for Claude Code — runs Claude, Codex, and Gemini in parallel for Judge-style synthesis

AdiaUI generative-UI system — compose strategies, retrieval, the harvested training corpus, and catalog-aware + LLM-judge validation. Emits A2UI protocol messages; pairs with @adia-ai/a2ui (the protocol runtime). Folded from @adia-ai/a2ui-{compose,retriev

Cost tracking, monitoring, and batch processing for LLM Judge Toolkit

Claude Code MCP tool for autonomous security testing (Agentic Hacking)

CompanionCourt — a public docket for pressure-testing AI companions: runner, subject adapter, dual judge families, scoring, run manifests, and CLI.