Skip to content

n8n Nodes Jev Classification

An n8n community node that classifies, scores and checks text with Jev, shaped like the built-in Text Classifier with one output branch per category plus a Needs Review branch, and built for volume with parallel requests and packed batches.

Stars
6
Language
TypeScript
License
MIT
Published by
Community
Author
khmuhtadin
Last verified
Oct 2026

About this project

An n8n community node that classifies, scores and checks text with Jev, TypeSafe AI's "System One" model. Jev does not generate text: you send it a piece of state (a ticket, a review, a JSON record) plus typed questions, and it returns typed answers with calibrated probabilities. This node wraps that as a Jev Classification node that behaves like n8n's built-in Text Classifier (one output branch per category plus a "Needs Review" branch), and is built for volume: it runs requests in parallel and can pack many…

Quoted from the project's README. Read the full README.

Highlights

  • Classify routes each item to a category output; Score rates text on 2 to 10 ordered levels; both emit calibrated probabilities and a confidence.
  • Fixed or dynamic categories: a list at design time for real branches, or names from a previous node or an AI Agent with a single Result output.
  • Parallel workers and multi-item packing, with the README citing provider measurements of 12.2x cheaper and 10x faster than separate calls.
  • Works against TypeSafe directly, OpenRouter and Vercel AI Gateway, with identical request and response shapes across all three.

Watch out

Self-hosted only, and n8n declined to verify the package because it is building a built-in classification node and does not verify community nodes that overlap with built-in functionality; the README states that decision was explicitly not about quality and that the package remains fully usable. The AI Agent tool variant only appears if the instance sets N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true. The credential Test can mislead on Vercel AI Gateway: it uses jev-latest and may fail there even when the node itself works, which is why the Test sends one tiny real request to POST <Base URL>/v1/systemone rather than a model list. Categories, levels and options are read once per run rather than per item, so they cannot be expressions there, while dynamic categories are evaluated per item. Cloudflare Workers AI is not among the listed providers. The accuracy-versus-cost figure comes from TypeSafe's own benchmark chart, and the README itself says to run your own comparison before relying on it. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

8GitHub stars
Shadcn registry search block that shows lexical hits instantly then re-ranks the top candidates with Jev intent scoring in one request, with keyword fallback on failure.
Jev Integrations & Adapters#community#jevbest#catalog-import
6GitHub stars
Community n8n node that adds a Jev judgment step to workflows, returning one of your options with probabilities so unsure items can go to review.
Jev Integrations & Adapters#community#awesomejev#catalog-import
n8n community node for TypeSafe's System One API, exposing yes or no, choice and score questions as workflow nodes, with an Evaluate Questions operation that batches several over one state in a single request.
Jev Integrations & Adapters#community#jevbest#catalog-import
0GitHub stars
ACP stdio agent that evaluates explicit Choice, Score and Noul questions as typed Jev answers inside any Agent Client Protocol client or IDE, driven by a task picker rather than free-form chat.
Jev Integrations & Adapters#community#awesomejev#catalog-import
69GitHub stars
Provider-neutral TypeScript runtime for System One decisions: write choice, noul, and score code once, then run it on TypeSafe Jev, local Reflex, any compatible /v1/systemone endpoint, or a custom provider.
Jev Integrations & Adapters#community#jevbest#catalog-import
25GitHub stars
Agent runtime with a terminal UI and a messaging gateway that keeps memory, self-built skills, session search, scheduling, and subagents across Telegram, Discord, Slack, WhatsApp, Signal, and CLI.
Jev Integrations & Adapters#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai