LangWatch Scenario is an end-to-end agent testing library for Python (>=3.10) that lets you define, run, and evaluate LLM agent scenarios. It supports async execution, built-in judges, red-teaming, and integration with LangWatch observability. Current version: 0.7.26, released 2026-04-28. Active development with frequent releases.
pip install langwatch-scenarioVerified import paths — ran on the pinned version, not inferred.
Create a ScenarioRunner with your API key and run a predefined scenario asynchronously.
Use underscore: pip install langwatch-scenario, import langwatch_scenario.
Use asyncio.run() in scripts or await inside async functions.
No code changes needed, but update license notices in your project if you were complying with AGPL terms.
No dependency data recorded yet.