Working with the Evals API

agent-skills-eval: An open-source test framework for measuring AI agent skill effectiveness

agent-skills-eval is an open-source test runner for evaluating AI agent skills (SKILL.md files) based on the Agent Skills standard from Anth

CoderLM API Reference: REPL Operations to HTTP Endpoints Mapping

This document provides a technical mapping between REPL operations and API endpoints for CoderLM, a tree-sitter-powered code indexing server

The Essential Role of Manual Data Review in AI Agent Evaluation

The article discusses the importance of evaluating AI agents, emphasizing that while automated evaluations (evals) are essential for testing

Vercel now supports the Bun Runtime

How the Debug Adapter Protocol Functions as a REPL Protocol

The article argues that the Debug Adapter Protocol (DAP), while designed for debugging, can effectively function as a REPL (Read-Eval-Print

Bun v0.6.6