Metadata-Version: 2.4
Name: reenact
Version: 0.0.1
Summary: Regression testing for LLM agents - record agent runs, replay them deterministically, and gate regressions in CI.
Project-URL: Homepage, https://reenact.dev
Author: Manas Dalvi
License-Expression: MIT
Keywords: agents,evals,langgraph,llm,regression-testing,replay,testing
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Topic :: Software Development :: Testing
Requires-Python: >=3.12
Requires-Dist: typer>=0.12
Description-Content-Type: text/markdown

# Reenact

**Regression testing for LLM agents.** Record an agent run once, replay it
deterministically offline at $0, and gate regressions in CI.

Think VCR.py, but for full multi-step agent trajectories: record -> replay ->
evaluate.

> **Status:** early scaffold, not yet functional. This `0.0.1` is a placeholder
> release that reserves the name on PyPI.
