# lema docs — Introduction

Models are interchangeable. Your reasoning isn't.

AI models are becoming a commodity — this quarter's best is next quarter's default. Your team's judgment isn't. What you decided, what you ruled out, and why it still holds is the asset that compounds — and today it evaporates into PR threads nobody re-reads. lema keeps it as a queryable, cited record of the why.

## The why, made queryable

- **The why, made queryable** — ask why and get a cited answer from your team's own decision graph: the rationale, not just the record.
- **Code is disposable, reasoning isn't** — agents write the code; lema keeps the why — the alternatives ruled out, the constraints that still apply — so it survives turnover.
- **The model changes, the knowledge stays** — the expertise lives in your graph, not the model's weights, and is served to any agent over MCP.
- **Automate up to the judgment** — lema does the labor (synthesize, cite, ground, draft) and never makes the call.

## What your agent gets

Tight, typed claims — chosen, rejected, constraint, consequence — each carrying its source, summarized not quoted, never whole documents. For example, "why did React move from classes to Hooks — and what was ruled out?":

- **chosen** (reactjs/rfcs#68): Hooks let function components hold state and lifecycle, so stateful logic can be reused without wrapper components.
- **rejected** (reactjs/rfcs#68): A mixins-style sharing mechanism was ruled out before Hooks — name collisions and implicit dependencies.
- **constraint** (rules of hooks): Hooks are called at the top level in the same order each render — never inside conditionals or loops.
- **consequence** (reactjs/rfcs#68): Classes stay supported; Hooks were additive and opt-in, not a migration mandate.

The rejected claim — the why-not — is the part no other tool surfaces.

## When it stays silent

When the record holds no decision on a question, lema says so. That is unknown, never approval — an honest gap beats a confident guess.

## How this doc is organized

- **Quickstart** — wire a repo and ask the graph.
- **Connect your repo** — sign in, mint a key, and serve your own decision graph over hosted MCP.
- **The why, not the what** — what a typed claim is, and why it always carries its source.
- **Fusion** — check whether an upstream project already argued an approach and ruled it out.
- **Tools** — the full set of tools an agent sees.
- **Verify** — the CI check on every pull request: did the diff do what the description says?
- **Public record** — shareable, no-signup URLs for public decisions, plus the no-auth read API.
- **Evaluation** — how faithful lema stayed to the source on repos it had never seen, misses included.
- **Plans & usage** — what is free, what Pro adds, and how usage is counted.

Record the why once, and every future session — human or agent — arrives grounded.