Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

n8n-nodes-typesafe-ai

n8n community node for TypeSafe's System One API with yes/no, choice and score questions, retry handling and an AI Agent tool.

Servicebeta
View on GitHub ↗

Overview

n8n-nodes-typesafe-ai brings TypeSafe's System One API (Jev) into n8n. It answers small typed questions about workflow data, yes/no probabilities, one-of-N choices and scores against ordered levels, with calibrated probabilities that the workflow can branch on, avoiding prompt engineering and free-text parsing.

The README documents GUI and manual installation on self-hosted instances, the API credential (sent as a bearer token), operations, an output reference, rate limits and retries, and an AI Agent tool so n8n agents can call it. It notes that n8n Cloud users must wait for n8n verification. It suits teams already automating with n8n who want reliable classification steps.

What the decision model decides

TypeQuestionAnswers
Yes / noYes/no question about the itemyes · no
ChoicePick one of N options for the item—
ScoreScore the item against ordered levels—

How it works

  1. Install via Settings > Community Nodes.
  2. Create a TypeSafe AI API credential.
  3. Configure questions in the node or expose it as an AI Agent tool.
  4. Branch on probabilities; retries handle rate limits.

Strengths

  • Documented rate-limit and retry handling.
  • AI Agent tool variant.
  • Clear install docs for Docker and queue mode.

Caveats

  • Self-hosted only until n8n verifies it.
  • Requires a TypeSafe key.

Getting started

In n8n: Settings > Community Nodes > Install, enter n8n-nodes-typesafe-ai, then add a TypeSafe AI API credential.

At a glance

Type
Service
Status
beta
Language
TypeScript
Runtime
n8n community node
Has code
yes

Use cases and integrations

How curated lists describe it

  • N8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities.

    hellogumbo/awesome-jev

Frequently asked questions

Can n8n AI Agents use it?

Yes, the README documents an AI Agent tool.

Does it work on n8n Cloud?

Not until n8n verifies the package; it works on self-hosted instances.

How are rate limits handled?

The README has a section on rate limits and retries.

Related projects

  • Sim

    Open-source workspace for building, deploying and monitoring AI agents and workflows, listed as integrating TypeSafe System One.

    ProjectproductionTypeScript
  • agentrun

    Workflow DSL for existing agents that uses Jev for the steps that are decisions and calls an agent only when investigation is needed.

    LibrarybetaTypeScript
  • n8n-nodes-jev

    n8n community node for Jev that adds a typed smart if-statement: choice, score and noul with probabilities in workflows.

    ProjectbetaTypeScript
  • n8n-nodes-jev-classification

    n8n Jev Classification node that branches items by category with a Needs Review branch, plus parallel and batched requests.

    ProjectbetaTypeScript
  • n8n-nodes-typesafe

    n8n node that sends a state and a map of typed questions to /v1/systemone in one request and returns per-question answers.

    ProjectbetaTypeScript
  • jev-orchestrator

    Python library to batch, gate, trace and calibrate thousands of typed Jev decisions, maximising questions per call.

    ProjectprototypePython