n8n-nodes-typesafe-jev
Community n8n node for asking multiple typed questions over workflow state.
# @n3ndor/n8n-nodes-typesafe-jev [](https://www.npmjs.com/package/@n3ndor/n8n-nodes-typesafe-jev) An n8n community node for [TypeSafe Jev](https://typesafe.ai), the TypeSafe System One model for fast, structured decisions. Jev returns typed decisions rather than generated prose. In a single node execution you can ask several independent questions about the same state and get back calibrated probabilities for classification, routing, verification and scoring. **No runtime dependencies.** The node calls the API over n8n's own HTTP helper rather than through a vendor SDK, so installing it adds one package and no transitive tree of its own. That is also a hard requirement for n8n verification, which does not permit runtime dependencies. Every release from 0.4.0 on is published from GitHub Actions with an npm provenance attestation, so the tarball can be traced to the commit and workflow that built it. Check it with `npm audit signatures`. > Unofficial and community-maintained. Not affiliated with, endorsed by, or supported by TypeSafe. ## Installation In n8n, go to **Settings → Community Nodes**, select **Install**, and enter: ```text @n3ndor/n8n-nodes-typesafe-jev ``` ## Credentials Create an API key in the TypeSafe console, then add a **TypeSafe API** credential in n8n and paste the key. Press **Test** to confirm it works. The credential is checked against the model list endpoint. | Field | Required | Notes | | --- | --- | --- | | API Key | yes | Stored encrypted by n8n and never written to output data | | Base URL | no | Defaults to `https://api.typesafe.ai`. Change only for a proxy or dedicated deployment. | ## Node configuration 1. Pick a **Model**, or leave the default. The dropdown is loaded from your account. 2. Supply **State** as plain text, a JSON o
