Intent-first unit testing framework for AI agents in Node.js and TypeScript.
Deterministic fault injection and autonomous resilience tests for DeepSeek Harness tools
Alethia's reference app + Playwright/PW-MCP benchmark. Fork to evaluate Alethia against your own agent or reproduce the numbers.
Preflight tests and decision receipts for AI agents. Lobster Trap (Veea) on the read-path + Zehrava Gate on the write-path, joined by one trace_id. MIT.
Reviewer/tester gate for web apps built with coding agents
Minimal test repository for exercising Pullery's issue-to-PR agent workflow against a reproducible defect.
Offline replay and validation for OpenAI-compatible tool-call transcripts
Skill automation test tin cậy, hiệu quả
Add a description, image, and links to the agent-testing topic page so that developers can more easily learn about it.
To associate your repository with the agent-testing topic, visit your repo's landing page and select "manage topics."