Metadata-Version: 2.4
Name: kneepoint
Version: 0.0.1
Summary: Find where your AI agent breaks: load, cost, and chaos testing for AI agents.
Project-URL: Homepage, https://kneepoint.dev
Project-URL: Repository, https://github.com/kneepoint-dev/kneepoint
Author: Mohan Chelluru
License-Expression: MIT
License-File: LICENSE
Keywords: ai-agents,chaos-engineering,llm,load-testing,performance-testing
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Software Development :: Testing :: Traffic Generation
Requires-Python: >=3.11
Requires-Dist: httpx>=0.27
Requires-Dist: jinja2
Requires-Dist: kneed
Requires-Dist: plotly
Requires-Dist: pydantic>=2
Requires-Dist: pyyaml
Requires-Dist: typer>=0.12
Provides-Extra: dev
Requires-Dist: build; extra == 'dev'
Requires-Dist: fastapi; extra == 'dev'
Requires-Dist: pytest; extra == 'dev'
Requires-Dist: pytest-asyncio; extra == 'dev'
Requires-Dist: ruff; extra == 'dev'
Requires-Dist: twine; extra == 'dev'
Requires-Dist: uvicorn; extra == 'dev'
Description-Content-Type: text/markdown

# Kneepoint

> Find where your AI agent breaks. Load testing, cost-per-resolved-task, and chaos engineering for AI agents.

**Status: pre-alpha, under active development — built in public.** The `0.0.1` PyPI release is a name reservation stub; nothing works yet.

- The Knee Point — the concurrency at which your agent's latency/quality cliff begins
- $/Resolved Task — spend divided by *successfully* completed tasks
- Resilience Score — resolution rate under injected chaos vs. clean baseline

Follow along: [kneepoint.dev](https://kneepoint.dev)

MIT licensed.
