Quickstart

Three steps: get a key, drop in the client, run it on your own workload.

1. Get an evaluation key

Visit the evaluation page, accept the terms, and copy your 90-day EVAL-… key. No fee, no card.

2. Install

The client is pure Python (standard library only). Drop the swc/ folder next to your code, or install the packaged wheel:

copypip install ./swc_runtime      # if packaged as a wheel/sdist

3. Integrate (the whole thing)

copyfrom swc import SWCOptimizer

opt = SWCOptimizer(license_key="EVAL-...", n=len(x0))
x = opt.start(x0)
for _ in range(rounds):
    p_hat = measure(x)            # your one measurement -> a statistic vector
    x = opt.step(p_hat, score=objective(x))
opt.end()

That is the full integration. Next: integration patterns for the two modes and a worked VQA example.