PyPI page
Home page
Author:
Rudrendu Paul, Sourav Nandy
License:
Apache-2.0
Summary:
Statistical regression testing for LLM agents. Get a p-value on whether behavior actually shifted between versions, not just whether one run looked different. Apache 2.0, self-hostable, no SaaS dependency -- a Promptfoo alternative for the statistical testing gap threshold-based eval tools don't cover.
Latest version:
0.1.9
Required dependencies:
jsonschema
|
numpy
|
scipy
Optional dependencies:
crewai
|
langchain-core
|
langgraph
|
mcp
|
mypy
|
openai-agents
|
pre-commit
|
pytest
|
pytest-benchmark
|
pytest-cov
|
ruff
Downloads last day:
6
Downloads last week:
64
Downloads last month:
180
7-day smoothing