devbrat-anand/agenteval-ai

pytest for AI agents — run agenteval tests and post results as PR comment

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
test_pathPath to test filesnotests/agent_evals/
fail_underMinimum average score threshold (0.0-1.0)no
eval_providerEval provider (ollama, openai, bedrock)no
eval_modelEval model nameno
python_versionPython versionno3.12

no outputs