Show HN: AgentCarousel – behavioral tests for AI agents, with signed evidence

Category: devtools

Tags: ai-testing, compliance, cli-tool

Score: 7.0/10 (Innovation: 7, Technical: 7, Documentation: 7, Utility: 7)

AgentCarousel is a CLI testing framework for AI agents that allows developers to define behavioral tests in YAML, run them in CI, and generate cryptographically signed compliance reports. It combines LLM-as-a-judge evaluation, regression testing, and compliance mapping (NIST, EU AI Act, HIPAA) into a single pipeline, which is a novel integration for agent reliability assurance.

Target audience: backend devs, ai engineers, devops

Repository: https://github.com/agentcarousel/agentcarousel · Rust · MIT · 8 stars

View on Hacker News