# lcf-strain-life

> An AI-agent-native toolkit for fatigue analysis of materials. A Python library
> plus an MCP server that reduce strain-controlled fatigue test data, fit the
> standard strain-life models, estimate constants from monotonic properties,
> count variable-amplitude histories, screen data for outliers, predict life,
> and cite the published source of every method, all callable by AI agents
> over MCP.

This file indexes the project for language models. All analysis uses true stress
and true strain. Stress is in MPa, strain is a dimensionless fraction, and the
fatigue exponents b and c are negative.

## Start here

- [README](README.md): overview, install, quick start for the library and the MCP server.
- [Agent usage guide](docs/AGENT_USAGE.md): the MCP tools, their units, and the compute, save, recall pattern.
- [AGENTS.md](AGENTS.md): guidance for agents working on the repository.

## Physics and changes

- [Physics review](docs/PHYSICS_REVIEW.md): every equation defined and cited, for specialist review. The typeset version with a sign-off table is [docs/PHYSICS_REVIEW.pdf](docs/PHYSICS_REVIEW.pdf).
- [Changelog](CHANGELOG.md): the chronological log of changes.
