ML Testing

This package is meant to help you define benchmarks for the [benchmark package](https://www.npmjs.com/package/benchmark) in a similar way as you can define unit tests with karma etc.

Node.js Evaluation Loop (NEL): module to run a Node.js REPL session

A small, sane JS micro-benchmark library

The headless Chrome/Chromium driver on top of Puppeteer. Take screenshots, generate PDFs, extract text and HTML with a production-ready API.

Benchmark.js mocha like command line interface

Agent evaluation harness. Judge sessions on success, tool usage, efficiency, methodology. Inspired by opencc.

A lightweight JavaScript event emitter.

A dead simple benchmarking framework

Benchmarking for forkeys

Determines whether a string is a valid javascript variable name. ES2015 and ES5 compatibility. Strict mode evaluation by default.

A lightweight JavaScript MIME type library.

Evaluate how prepared your codebase is for autonomous AI coding agents

No description available

Evaluation condition block for Tripetto.

CLI benchmark system for tracking skill versions, scoring performance, and comparing improvements

CLI entry point for AgentV

AgentID core SDK - cryptographic identity, manifests, signing, verification, and policy evaluation for AI agents

A set of tscircuit problems to benchmark autorouting (currently 16 circuits in `lib/`).

consys is a flexible tool to evaluate models using generic and readable constraints.

Allows to define a value in post of an evaluation of a string whose pattern is like img[srcset]