opencx-labs/zevals

Simple, practical AI agent testing in TypeScript

39
/ 100
Emerging

This tool helps developers rigorously test their AI agents, especially those handling complex conversations or using external tools. It takes your existing AI agent code and defines specific scenarios, allowing you to set clear, pass/fail expectations for how the agent should behave. The result is a robust validation that your AI agent performs as intended in real-world interactions.

Use this if you need to ensure your AI agent reliably handles multi-turn conversations, makes correct tool calls, or follows specific interaction logic without needing complex metric tracking.

Not ideal if your primary focus is on detailed performance metrics, fine-grained accuracy scores, or if you prefer a framework that imposes a specific testing methodology.

AI agent development LLM testing conversational AI software quality assurance AI assistant validation
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

TypeScript

License

MIT

Last pushed

Dec 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/opencx-labs/zevals"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.