# VerifiedX LangGraph starter

Protect a LangGraph node before it mutates graph or store state.

This starter shows two things:

- a grounded durable memory write that is allowed
- a graph update that gets blocked because it claims a prerequisite write already happened

It is intentionally model-free so you can see the LangGraph boundary clearly before you plug in your own model loop.

## Run it

```bash
python -m venv .venv
. .venv/bin/activate
pip install -r requirements.txt
verifiedx doctor
```

Set env:

```bash
export VERIFIEDX_API_KEY=...
export VERIFIEDX_BASE_URL=https://api.verifiedx.me
```

Run:

```bash
python run.py
```

What to check:

- `artifacts/scenario_report.json`
- `artifacts/verifiedx_diagnostics.jsonl`

You should see one allowed memory write and one `replan_required` graph update with safe next steps.