Are the benchmark numbers real?

Treat them as author-reported, not independent measurements. Cost per row, sub-2-second detection, and the comparison table against native AI and webhook servers all come from the repo, so verify on your own database before relying on them.

How does this compare to Notion native AI or a webhook server?

Native AI returns plain-text guesses with manual triggers, and webhook servers add hosting plus LLM bills with minute-scale aggregation. This polls rows directly, returns calibrated probabilities, and holds uncertain entries in visual review cards.

What happens when Jev is uncertain about a row?

They go to a native review queue instead of being written silently. Jev returns typed outputs with confidence, and entries below the bar wait for human approval rather than overwriting properties.

What do I install to run it headless versus in the app?

For the app, download the 2.8 MB zip, drag JevNotion.app to /Applications, and enter credentials in Settings. For headless use, set NOTION_TOKEN and TYPESAFE_API_KEY, then run npx scan, apply, or install.

Where are my Notion and Jev credentials stored?

In the macOS app, credentials go into Apple Keychain with no plaintext tokens on disk. For the CLI you put NOTION_TOKEN and TYPESAFE_API_KEY in .env. The integration token comes from a Notion internal integration and the Jev key from typesafe.ai.

What are the four CLI commands?

npx jev-notion runs an automated one-command sync, npx jev-notion scan prints suggestions without writing, npx jev-notion apply applies approved suggestions from JSON, and npx jev-notion install registers it as a background launchd daemon on macOS.

What happens to a row Jev is not confident about?

Jev returns typed outputs with a confidence, and the app holds entries below a roughly 60% bar in a native review queue rather than writing silently. Uncertain entries wait for human approval instead of overwriting database properties.

CommunityJev Demos & Experiments

Jev Notion

Fills Notion database properties with calibrated Jev judgments through a native macOS SwiftUI app and a terminal CLI, polling row edits and routing uncertain entries to review.

See highlights

Open github.com

Stars: 4
Language: TypeScript
License: MIT
Published by: Community
Author: jeffloo886
Last verified: Oct 2026

jeffloo886/jev-notion

User repository on GitHub

View on GitHub

🚀 Blazing-fast native macOS menu bar companion for Notion. Pure Swift & SwiftUI (<3MB), 8 languages.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Fill Notion database properties with calibrated AI judgments. Second-level latency (≤2s) • Micro-cent cost ($0.00004/row) • Native macOS App (SwiftUI) + CLI • Zero Server. 📦 Download macOS App (2.8MB) • ⚡ Run in Terminal • 🌐 8-Language Preview • 📊 Benchmarks. Experience seamless, real-time hot-switching across 8 world languages. Click any language tab below to see full-resolution macOS app screenshots: 🇺🇸 English (Default) — Click to expand. 🇨🇳 简体中文 (Simplified Chinese) — Click to expand.

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

Tagscommunity awesomejev catalog-import

Works forJev for Classification

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Adaptive polling picks up row edits in under 2 seconds instead of waiting on aggregated webhook queues.
Requests roughly $0.00004 per row with input-only billing and free output, with uncertain entries held for review.
Ships a 2.8 MB macOS app with an 8-language hot-switching interface plus npx scan, apply, and install commands.
Credentials come from a Notion integration token and Jev key in .env, with macOS keys kept in Apple Keychain.

Watch out

Comparison-table speed and cost figures are author-reported, and background sync needs Notion and Jev credentials configured. 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

laya-server

Self-hosted Docker service and web UI that packages Laya structured-decision inference behind a compatible System One endpoint.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

1Panel-dev/laya-serverPython

jot

General-purpose System One agent where Jev chooses tools and arguments while Jot executes them and loops until it can reply.

Jev Demos & Experiments#community#awesomejev#catalog-import

Community

runta-dev/jotTypeScript

jev-reflex-autonomy-lab

Browser drone-fleet lab where TypeSafe Jev steers each drone as fast reflexes and an optional planner offers one-use strategy advice when confidence drops, without pausing control.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

khordoo/jev-reflex-autonomy-labTypeScript

x-scanner

Chrome extension that sends each X post to Jev with six typed questions in one call near the viewport, then renders a behavior chip under the post plus a session cost and latency panel.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

oso95/x-scannerTypeScript

lkclean

Manifest V3 Chrome extension in TypeScript that sends each LinkedIn post to Jev and collapses bait, self-promo, off-topic, and sponsored posts into a one-line bar with reasons and scores.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

stefw/lkcleanTypeScript

flue-jev-demo

Standalone Flue example that routes support chat through Cloudflare Workers AI, using gpt-4o-mini for chat and Jev for typed intent and urgency routing.

Jev Demos & Experiments#community#awesomejev#catalog-import

Community

matthewp/flue-jev-demoTypeScript

From the Jev guides

Original write-ups on what this entry is for.

Per-Tick Decisions in Games

Sep 28, 2026

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.

Jev Demos & Experiments#gaming#agents#control

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai