AI coding agent evaluation framework with Vitest-like DX

Vercel AI SDK adapter for the Assay LLM evaluation framework

Jest integration for the Assay LLM evaluation framework

Coding agent evaluation framework

Evaluation framework for AI agent skills — measure whether capabilities actually work

Agent-native ML experiment tracking and model evaluation framework for reproducible machine learning research

A CLI for the Tally evaluation framework

LLM agent evaluation framework — define agent behaviour in YAML, evaluate against multiple models, compare results

Use Custom Media Queries in CSS

Core evaluation engine for the Assay LLM evaluation framework

Prompt testing and evaluation framework for Prompd

Core types, configuration, and utilities for the Tally evaluation framework

Snapshotable JavaScript runtime via WebAssembly. QuickJS-NG compiled to WASM with snapshot/restore support.

TypeScript client for the AumOS agent-eval evaluation framework — benchmarks, metrics, and run comparisons

Symbolic computing and numeric evaluations for JavaScript and Node.js

Prompt evaluation framework (3-layer A/B/C)

A TypeScript evaluation framework for running concurrent evaluations with progress tracking and result persistence

Open-source AI agent evaluation framework — benchmark MCP servers, A2A agents, and API-first agent services

flagd-core contain the core logic of flagd [in-process evaluation](https://flagd.dev/architecture/#in-process-evaluation) provider. This package is intended to be used by concrete implementations of flagd in-process providers.

AI Literacy Framework - Evaluation tool for Sanity documentation