Run local twins of every external service your AI agents reach for.

Two commands. Your external services, local.

$ npx wondertwin init stripe plaid
✓  Stripe twin v3.2 ready on localhost:4111
✓  Plaid twin v2.0 ready on localhost:4112

$ wt status
2 twins running · drift-aligned · 0 errors

No mocks to maintain. No vendor sandboxes to stitch together. Your agent talks to your dependencies locally.

Pro WonderTwins stay current.

Continuously calibrated against production behavior.

OSS twins ship as frozen snapshots. Pro twins observe production and stay aligned.

Three components. One local binary.

WonderTwin: Registry · Runtime · Twins

01

The Registry

10 Open Source twins. 26 Pro twins. Your stack pulls what it needs.

02

The Runtime

Composes Stripe, Plaid, Shopify, Twilio and more into one local environment — your full vendor stack, running together. CLI- and MCP-compatible. Single Go binary, milliseconds to launch, developer laptop or CI runner.

Discover via MCP →

03

The Twins

Local, stateful, behavioral models of each external service. Adaptive Software Twin (Pro) — drift-aligned through continuous calibration. Production-fidelity (Pro) — real vendor rate limits, deterministic replay.

Frequently asked

The four questions engineers ask before installing.

• 01 How is a WonderTwin different from a mock? +

  A mock returns a shape — a canned response you wrote, identical every time, with no memory of the calls before it. A WonderTwin runs a model: it holds the service’s state and enforces its rules, so each response is computed from what you’ve actually done, not looked up from a fixture. That’s what makes it stateful (a transfer moves the balance, and the next read reflects it), distribution-faithful (it counts your calls and enforces the real rate limits and latencies), and failure-accurate (it runs the service’s validation, so a bad idempotency key fails the way production would).

  So a mock tells you whether the call shape was right; a WonderTwin tells you whether your code actually works when the service behaves like itself — with no mocks to maintain and no vendor sandboxes to stitch together.

• 02 Can my agent pull in new WonderTwins on its own, if needed — and how does billing work? +

  Yes. Your agent talks to the MCP and can discover and call any twin in the catalog as it works — it doesn’t have to be wired up ahead of time.

  Open-source twins are free. When your agent calls a Pro twin, that twin is added to your subscription, billed per organization (not per seat). Each Pro twin is its own line — including each version you keep running. If you’re holding a twin on v3.1 after the service has moved to v3.2, that’s two Pro twins. You’re billed for the Pro twins you actually run.

  Current pricing →

• 03 How do I install and run a twin? +

  Two commands:

  
                        $ npx wondertwin init stripe plaid
  ✓  Stripe twin v3.2 ready on localhost:4111
  ✓  Plaid twin v2.0 ready on localhost:4112
  
  $ wt status
  2 twins running · drift-aligned · 0 errors
                      

  That’s it — the twins run locally as one binary. Point your existing SDK at the local port and your calls work, offline and unlimited.

• 04 What’s free in open source, and what needs Pro? +

  Open source (MIT, free forever): the twin catalog’s open-source tier, the wt CLI, the MCP server, and the local runtime. Open-source twins ship as frozen snapshots — they model the service as of their release.

  Pro (paid, per-twin subscription): adaptive twins that stay aligned as the real service changes, version pinning, drift detection, and the Pro-only services in the catalog.

  The difference in one line: open-source twins are frozen; Pro twins stay current.

More questions answered on the full FAQ → /faq

Built by people who hit this problem at every prior company.

Max & Dot

Max & Dot live throughout WonderTwin — in the CLI output, in error messages, in this site. Max is the clone — running, energetic, slightly reckless. Dot is the original — observing, precise, perpetually worried about what she hasn't seen. Together: observation meets action.