A lightweight evaluation layer for AI systems with structured cases, checks, and summaries.
A flexible math expression evaluator
evaluate statically-analyzable expressions
Simple JavaScript expression evaluator
Evaluate node require() module content directly
Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.
Mathematical expression evaluator fork with exports map, prototype pollution and code injection security fixes
require or eval modules
Mark scopes for deopt which contain a direct eval call
Evaluation library for the MongoDB Assistant API.
Get callsites from the V8 stack trace API
JavaScript expression parsing and evaluation.
Alias for eval global.
Safely evaluate JavaScript (estree) expressions, sync and async.
A simple cache for a few of the JS Error constructors.
Eval a string with a passed scope
A library for teleporting rich data to another place.
LLM eval & testing toolkit
decycle your json
Mathematical expression evaluator
TypeScript execution environment and REPL for node.js, with source map support
Provides metadata and conversions from repository urls for GitHub, Bitbucket and GitLab
Parse Content Security Policy directives.
MCP server that exposes Mneme to Claude Code, Cursor, Continue, and other AI clients
No description provided.
No description provided.