Is the ~100ms latency a guarantee for my workflows?

No. The digest says the ~100ms headline is a target use case, not a guarantee, and cites roughly 70-500ms end to end with network, workload, queueing, and retries all mattering. Log the latencyMs field on your own flows.

Can I install this on n8n Cloud as a verified node?

No. The digest states it is not an n8n-verified package and that verification rules prohibit runtime dependencies, while this package depends on the official TypeSafe SDK. Target self-hosted n8n.

Does a schema-valid answer mean the decision is correct?

No. A schema-conforming answer can still be the wrong valid value. The digest warns semantic errors remain and prompt-injection detection is probabilistic, so keep authorization and side effects in workflow code.

Should I pin the model version or use the latest alias?

The default pins a full release ID for stability, while jev-latest is a moving alias. The digest advises pinning for production after evaluating thresholds and logging the returned model field that actually answered.

How do I install the node on self-hosted n8n?

Open Settings, then Community Nodes, then Install, enter n8n-nodes-typesafe-jev, then create a TypeSafe Jev API credential from your console.typesafe.ai key and add the node to the canvas.

What state formats does the node accept?

Auto takes objects and arrays directly and parses strings starting with { or [, JSON parses strictly and stops on invalid JSON, and Text sends the string unchanged. Binary attachments pass through but are not sent to Jev.

What does a Score return?

An expected score from 0 to N-1 that can be fractional, for example 1.6, with a probability per level, a rubric legend and API confidence; it is not rounded to a label or normalised to 0 to 1.

CommunityJev Integrations & Adapters

n8n Nodes Jev — rahulthakore16

Community n8n node that adds Jev Choice, Score, and Noul questions to workflows, keeping native answers, model version, token usage, and latency for confidence routing.

See highlights

Open github.com

Stars: 2
Language: TypeScript
License: MIT
Published by: Community
Author: rahulthakore16
Last verified: Oct 2026

rahulthakore16/n8n-nodes-jev

User repository on GitHub

View on GitHub

Jev by TypeSafe AI for n8n: typed decisions, probabilities, and confidence-aware workflows

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

This is one of several Jev listings for the same project. The canonical entry is n8n Nodes Jev — vibe-with-me-tools.

About this project

Add a frontier-intelligence 'smart if-statement' to any n8n workflow — typed decisions with calibrated confidence in 100ms, no prompt engineering. Turn emails, support tickets, user prompts, and JSON state into decisions your workflow can use directly. Jev by TypeSafe AI evaluates typed questions rather than generating text for you to parse. Choice: classify into one of your labels, with probabilities and confidence. Score: get a fractional score against an ordered rubric, with probabilities and confidence.

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

Tagscommunity github

Works forJev for Classification

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Offers Choice, Score, and Noul operations with unique answer keys and multiple same-primitive questions per call.
Defaults state to the incoming JSON item and supports auto, strict JSON, and verbatim text handling.
Preserves answers, normalized decisions, usage, model version, latency, and warnings for If and Switch routing.
Applies Noul thresholds locally without sending them to the model, leaving Noul confidence null.

Watch out

Self-hosted n8n targeting current releases with Node 22+; not an n8n-verified package, so check your install policy. 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

jev-qa-demos

Video companion code showing Jev for QA work through the Vercel AI Gateway, from CI failure triage to guardrails, grounding checks, and local Ollama runs.

Jev Integrations & Adapters#community#github

Community

gauravkhuraana/jev-qa-demosTypeScript

omp-plugin-jev-router

Oh My Pi extension that asks Jev whether each interactive prompt is simple or advanced, then switches the OMP model role and thinking level without rewriting the prompt.

Jev Integrations & Adapters#community#github

Community

atulify/omp-plugin-jev-routerTypeScript

SiYuan

46.7k

Privacy-first, self-hosted personal knowledge management system with block-level references and a local-first Markdown editor; the project integrates Jev's decision model for high-speed document classification, flashcard intent categorization and automated tag routing.

Jev Integrations & Adapters#community#note-taking#knowledge-base

Community

siyuan-note/siyuanTypeScript

Eliza

19.6k

Open-source TypeScript agentic operating system: a core runtime, app for web and mobile, CLI, cloud services and first-party plugins. The directory's curated summary reports it integrates TypeSafe System One decision services for sub-100ms intent classification, action dispatching and confidence-gated tool execution.

Jev Integrations & Adapters#community#agents#framework

Community

elizaOS/elizaTypeScript

Inbox Zero

12.4k

Open-source AI email assistant (Next.js, Postgres, 12k+ stars) with a decision-model layer that can run on openrouter:typesafe/jev-1.13: Jev-backed questions cover rule selection, cold-email detection, thread status, recurring patterns, unsubscribe pages, and sender categorization, each with evals.

Jev Integrations & Adapters#community#email#gmail

Community