Universal library for evaluating AI models

AI/LLM judge matchers for Playwright — toPassRubric/toScoreAtLeast/toMatchImage over Ollama, OpenAI-compatible endpoints (OpenAI/OpenRouter/NVIDIA/Groq/…), and native Claude

Semantic conflict adjudication for Credence: declarative conflict families, cached verdicts, optional LLM.

LLM-judged CLI test runner — define test cases in YAML, execute commands, let an LLM judge PASS/FAIL. Outputs JSONL trace.

Brain-Computer Interface (BCI) neural signal transcription addon for qvac, powered by whisper.cpp

Testing utilities, mock providers, fixtures, and eval framework for ElsiumAI

Governed structured-output LLM pipeline: rate limit → spend caps (per-user + global circuit breaker) → cache → provider-chain failover → Zod validation → usage logging → LLM-judge, with a deterministic mock provider for CI.

skill-harness engine — spec, discover, run, LLM-judge grade, score, results (internal API)

mutagent-evaluator: a generic, subject-agnostic AI-agent auditor — reviewer, never executor. Audits any skill/agent against a generated subject profile and emits a 4-tab master-audit report.

Agentic visual regression for BlazeDiff. Auto-discovers routes, captures deterministic screenshots, runs CI checks.

No description provided.

SOTA NPM module for agentic processes using local or cloud LLMs.

Gated orchestrator for AI-assisted software development

Autonomous agent team harness — coordinate a lead and participant agents in one async session, with eval, benchmark, and trace tooling to prove the changes worked.

Render web and SwiftUI evidence, run explicit visual judgment, and trace ADS UI decisions.

ESLint JavaScript language implementation

MoltNet agent runtime — coding-agent-agnostic Task execution loop

Command-line interface for the PropLine player props betting odds API. Wraps the propline SDK with pretty-printed tables and JSON output.

skill-harness harness adapters — pi runner + claude-code judge routing (internal API)

Standalone CLI tool for verification tasks