Jev directory
CommunityJev Integrations & Adapters
TypeSafe n8n Community Node
n8n community node that adds a TypeSafe resource to workflows, exposing Get Many Models and Ask Questions operations against the TypeSafe API. Generated from OpenAPI 0.2.0 and authenticated with a bearer token credential.
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Distributed on npm as @nativeship/n8n-nodes-typesafe and installed as an n8n community node.
- Exposes two operations: GET /v1/models (Get Many Models) and POST /v1/systemone (Ask Questions).
- Authenticates with a generated bearer token credential configured in n8n before use.
- Generated from OpenAPI 0.2.0 with template 1.1.0; generated files are platform-managed.
- Neither operation defines a retry contract or a pagination contract.
Questions about this entry
Short answers drawn from the linked project or page.
Install the community-node package in n8n, then add the TypeSafe node to a workflow, select a resource and operation, configure its parameters, and execute the workflow.
A generated bearer token credential, configured in n8n before using the node. The package documentation states authentication is set up through that credential rather than through node parameters.
Two: GET /v1/models, surfaced as Get Many Models, and POST /v1/systemone, surfaced as Ask Questions. Each is selected as a resource and operation pair inside the node.
No. Both listed operations declare a Retry Contract of none and a Pagination Contract of none, so neither behaviour is built into the generated node.
Connect a Manual Trigger to the TypeSafe node and then to a destination node, select an operation, run the workflow, and inspect the returned items.
Run npm install, npm run build and npm run lint. npm run dev starts a local n8n development instance, where the integration is found by its TypeSafe display name.
The generated files are platform-managed and will be overwritten during regeneration, so local edits to them are not preserved across a rebuild.
More Jev resources like this
LangChain.js integration for TypeSafe System One models. It wraps the jev classifier as a Runnable that returns typed choice, score, and noul answers with calibrated probabilities, plus agent middleware for model routing and tool gating.
Jev Integrations & Adapters#typescript#sdk#routing
Community
Effect provider package that serves the DecisionModel capability with Jev, the System One model answering typed questions with probabilities instead of text. Defines classify, rate, and probability decisions answered in one call, with typed AiError mapping.
Jev Integrations & Adapters#typescript#sdk#classification
Community
TypeScript package that implements the IDecisionModel interface for @mcp-abap-adt/llm-agent on top of @typesafe-ai/sdk, letting an agent ask Jev typed yes/no, choice, and score questions about a state and get numbers back.
Jev Integrations & Adapters#typescript#sdk#agents
Community
Official AI SDK provider package for TypeSafe AI. Through its decisionModel, used with the AI SDK's experimental_decide, it decides answers to Choice, Score, and Boolean questions using TypeSafe's System One models such as jev-latest.
Jev Integrations & Adapters#typescript#sdk#classification
Community
TypeScript service and library that places Jev between a PBX such as Asterisk or FreePBX and call destinations, classifying caller intent into predefined routes. Each route maps to an explicit PBX action, with low-confidence or unhandled calls sent to a fallback route.
Jev Integrations & Adapters#typescript#routing#github
Communityrayanweragala/jev-call-router
n8n community node that sends a state and a map of Noul, Choice, and Score questions to the System One endpoint in one request, returning calibrated probabilities and confidence for workflow branching.
Jev Integrations & Adapters#github#typescript#guardrails
Communityzampierid4p/n8n-nodes-typesafe
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.