Universal library for evaluating AI models
Braintrust Autoevals integration for ZEvals
Evaluation library for the MongoDB Assistant API.
LLM evaluation framework with batch processing and data sources
Unit testing for AI Agents — test, evaluate, and track your AI experiments
A minimal, vitest-native evals library for LLM applications
A commandline-utility to interactively build complex shell pipelines
Derive macros for Bevy event and message types - generates Event, Message, and EntityEvent types from enum variants with support for triggers, observers, buffered messaging, and entity propagation