Results for eval-metrics

Canonical diagnosis prompts + Zod Diagnosis schema + pure eval-metrics for the reactlens / nativelens AI failure-diagnosis loop. Pure helpers only — no LLM SDK dep.

RAG evaluation metric scorers: faithfulness, relevance, context precision/recall

Production-grade primitives for building agentic AI systems on the Anthropic SDK: hybrid RAG with RRF, eval metrics (recall@k, NDCG, tool-call F1), cost-aware model router, and prompt-cache planning. Extracted from OnGravy.

evaluate statically-analyzable expressions

OpenTelemetry metrics SDK

Simple JavaScript expression evaluator

OpenTelemetry Collector Metrics Exporter allows user to send collected metrics to the OpenTelemetry Collector

Evaluate node require() module content directly

OpenTelemetry Collector Metrics Exporter allows user to send collected metrics to the OpenTelemetry Collector using protobuf over HTTP

Mathematical expression evaluator fork with exports map, prototype pollution and code injection security fixes

Native metrics collector for libuv and v8

A flexible math expression evaluator

OpenTelemetry Collector Metrics Exporter allows user to send collected metrics to the OpenTelemetry Collector

Client for prometheus

require or eval modules

Buffered metrics reporting via the Datadog HTTP API

Mark scopes for deopt which contain a direct eval call

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.

PM2.io NodeJS APM

Easily measure performance metrics in JavaScript

Unpack capsize font metrics from fonts