A simple TypeScript runner --------------------------
Canonical diagnosis prompts + Zod Diagnosis schema + pure eval-metrics for the reactlens / nativelens AI failure-diagnosis loop. Pure helpers only — no LLM SDK dep.
Agent evaluation framework — prove whether agent changes improved outcomes with reproducible evidence.
Read node.js file and eval it
This is the parser and evaluator used in the basho project. For documentation see https://www.github.com/jeswin/basho.
Mailwoman neural-classifier weights for locale 'en-us'. Data-only package — loaded by @mailwoman/neural at runtime.
Query json with jsonpath expressions
Read-Evaluate-Print-Loop environment for JavaScript
Convert math expressions between postfix (RPN) and infix notations and evaluate them
AI/LLM integration for the Kaiord health & fitness data framework
Core types, schemas, and domain models for RAG evaluation
An ESLint® plugin that detects and mitigates security-related issues for DevExpress projects.
Parse makefiles
Static obfuscation detector for npm lifecycle scripts — supply chain attack prevention
Evaluate numerical expressions
Multi-provider skill evals with integration mocks
Mathematical expression evaluator
SWE-bench Pro evaluation harness for nexus-agents (731 multi-language instances, ScaleAI/SWE-bench_Pro)
Command-Line Interface scripts and releated utilities.
an override replacement for @protobufjs/inquire
Compile eval calls with string literals
Computer Algebra System in Coffeescript
<div align="center"> <img src="spassr.png" alt="routify" width="400" /><br> </div>
Corelay Mesh eval pipeline — test suites, LLM-judged scoring, deploy-gate thresholds.