opencx-labs/zevals
Simple, practical AI agent testing in TypeScript
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.
Stars
9
Forks
2
Language
TypeScript
License
MIT
Category
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.
Higher-rated alternatives
lobehub/lobehub
The ultimate space for work and life — to find, build, and collaborate with agent teammates that...
Pipelex/pipelex
Declarative language for composable Al workflows. Devtool for agents and mere humans.
strands-agents/sdk-typescript
A model-driven approach to building AI agents in just a few lines of code.
lemony-ai/cascadeflow
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside...
agents-flex/agents-flex
Agents-flex is A Lightweight Java AI Application Development Framework.