

EvalCore
Snapshot-test AI behavior in CI
什麼是 EvalCore?
EvalCore is a single-binary test runner for LLM apps and agents. Define cases and scorers in YAML, run local targets on every PR, and replay model or judge calls offline for $0. Use REST or shell targets, baselines, trials, model comparisons, and OTel traces.
截圖
?
還沒有評論,來搶沙發吧!
X 上關於 EvalCore 的真實討論
去 X 發文






