Vibeleaderboard
Index / tool
Visit github.com
Category
Developer Tools
Rank
No. 1717Tools index
Pricing
Open Source
Type
TOOL
GitHub
12 stars
Date

About

An open-source test runner for coding agents and agent skills. It runs real workflows in fresh temporary directories and asserts on tool calls, commands, files, HTTP requests and final answers, so one model does not need to judge another. The same scenario can run across Claude Code, OpenAI Codex, OpenCode, Pi, Cursor CLI and Google Antigravity CLI to expose behavior that differs between them, and experimental CLI and MCP mocks supply controlled responses.

Tags

testingai-agentsmcpclievalsclaude-code

Tech Stack

Node.js

Comments (0)

No comments yet

Editorially curated, with community endorsements as a secondary signal. Corrections welcome.