Reusable Vue 3 components, composables, router factory, and inspector registry for the evals-viewer framework — a lightweight, configurable viewer for LLM evaluation results.
Vite plugin and middleware exposing the filesystem-backed evals-viewer API, plus reusable building blocks (composeLoaders, datasetCaseLoader, …) for assembling a custom caseDataLoader.
A JavaScript library to display 360° panoramas
Harness-backed AI testing on top of Vitest.
GitHub Action for evaluating MCP server tool calls using LLM-based scoring
LLM eval & testing toolkit
Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c
`@mastra/evals` ships a collection of scoring utilities you can run locally or inside your own evaluation pipelines. These scorers come in two flavors:
A library to create a trace of your node app per Google's Trace Event format.
Document viewer for react. Renders online/local documents.
A React wrapper for Photo Sphere Viewer, to display 360° panoramas with ease.
Test your LLM-powered apps with a TypeScript-native, Vitest-based eval runner. No API key required.
Continuation of a simple and beautiful text diff viewer component made with diff and React
🛵 The stylish Node.js middleware engine for AWS Lambda (core package)
Cornerstone3D Core
View your Tailwind CSS config file...visually!
Easily display interactive 3D models on the web and in AR!
Offline evaluation framework for Output.ai workflows
JavaScript API for Logfire - https://pydantic.dev/logfire
Claude Code Logger visualization management tool
Graphviz Models for Object-Oriented Programming
Angular 5+ component for rendering PDF
parses xunit xml into xunit viewer
Create and modify PDF files with JavaScript