ML Testing

azk's benchmarking tool

Perform element-wise evaluation of one or more input arrays according to provided predicate functions and count the number of elements for which all predicates respectively return `true`.

HTTP-based side-by-side benchmark framework

Super simple benchmark tool

chess-tactics is an opinionated tactic detection library that finds a tactic, the pieces involved, and the tactical sequence given a position and its engine evaluation.

CLI for running, testing, and evaluating SCARF benchmark applications.

Advanced JSON-based rule engine with nested conditions, async evaluation, and flexible action system. Perfect for business rules, workflows, and decision automation.

Benchmark framework for evaluating AI coding agent architecture patterns

Poker hand evaluator with comprehensive test suite

Performance benchmarking tool for NodeJS.

Slice is a TypeScript-first React UI kit with theme tokens, utility hooks, optional Zustand stores, Storybook docs, and benchmark tooling.

A secure TypeScript expression evaluator for dynamic form validation and conditional logic with support for context variables, form fields, and custom functions

<h1 align="center"> <img src="https://raw.githubusercontent.com/RafaelGSS/bench-node/refs/heads/main/assets/logo.svg" alt="Bench Node logo" /> Bench Node </h1>

Unified types for EvalForge agent evaluation system

Evaluation library for the MongoDB Assistant API.

TypeScript SDK for Mankinds AI Evaluation API

TypeScript implementation of the verifiers framework for RL environments

translate the evaluation of a function that takes multiple arguments into evaluating a sequence of functions, each with a single or more arguments

Optimal evaluation of some lambda terms