{"id":"io-github-rudrendupaul-agent-eval","name":"io.github.RudrenduPaul/agent-eval","title":null,"description":"Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.","category":"developer-tools","categories":["developer-tools","agents-and-memory","ai-and-media"],"flags":[],"users_30d":0,"health":{"status":"no_remote","latency_ms":null,"tool_count":null,"auth":null,"checked_at":null},"remote":false,"pending":false,"install_link":"https://toolfindr.dev/add?server=io.github.RudrenduPaul%2Fagent-eval&ref=tool-finder","details_url":"https://toolfindr.dev/servers/io-github-rudrendupaul-agent-eval","health_error":null,"repo_url":"https://github.com/RudrenduPaul/agent-eval","website_url":null,"version":"0.1.8","remotes":[]}