Automated AI researcher that improves AI systems
Evaluation of DMN 1.3 decision tables, limited to S-FEEL (Simple Friendly Enough Expression Language)
Implementation of @shexjs/neighborhood-api which gets data from an @rdfjs/dataset
Opinionated open-source eval harness for RAG and agent apps built on Claude
Assertion framework for AI agent evaluations - supports skill invocation checks, build validation, and LLM-based judging
eval code in vm module, but always strict mode.
Claude Code Plugin for CodingBuddy - PLAN/ACT/EVAL workflow, specialist agents, and reusable skills
JSON Eval RS for bundlers (Webpack, Vite, Next.js, etc.) with ergonomic API
Module, which assists in supporting transitional (from 'eval' to 'require') BEM formats.
A configurable eval function, which uses jsep to parse expressions. The generated result is evaluated w.r.t. a supplied object context.
Mathematical expression evaluator
Merge Content-Security-Policy directives
Runtime kernel for the Maestro agent platform — tool envelope, tool definition factory, base context, port interfaces, and AI-SDK + MCP adapters.
Evaluate html table with cheerio - html engine of jsreport-html-to-xlsx
Rules Engine expressed in simple json
Safely eval a JavaScript expression within a scope
High-performance JSON Logic evaluator with schema validation for React Native
AI engine — providers, agents, tools, streaming, middleware
BenchRouter target-repo setup CLI
JavaScript client for running remote evaluations with Scoundrel.
Javascript Expression Language: Powerful context-based expression parser and evaluator
TypeScript SDK for Angie AI assistant
MCP server for the Hetzner Cloud API — manage servers, networks, volumes, and more
Toolkit for testing and evaluating AI agent skills