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

mood-pixels

Small Next.js mood tracker where Jev classifies a daily check-in into one of five moods and a 1-5 energy score.

DemoprototypeMIT
View on GitHub ↗

Overview

Mood Pixels is a small mood-tracking web app. You write a few words about your day, and a server route sends the text to TypeSafe's Jev, which classifies the check-in as Sparkly, Cozy, Tired, Sad or Frustrated and gives an energy score from 1 to 5 along with a short self-care nudge. The result colours that day in a Year in Pixels calendar for 2026.

Results are stored per date in the browser's localStorage; the check-in text itself is sent for analysis but not saved. There are no accounts, so data does not sync across devices. It is a compact example for developers learning how to call Jev from a Next.js API route and map the answers to a UI.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich mood best describes this check-in?Sparkly · Cozy · Tired · Sad · Frustrated
ScoreEnergy level1 · 2 · 3 · 4 · 5

How it works

  1. User writes a short check-in and clicks Log Vibe Check.
  2. Server route /api/jev sends it to Jev with typed questions.
  3. Mood and energy score come back with a self-care nudge.
  4. The day is coloured in the calendar and saved to localStorage.

Strengths

  • Simple, readable example of a Jev call from Next.js.
  • Check-in text is not stored in the browser.
  • MIT licensed.

Caveats

  • Calendar fixed to 2026; no history or editing view.
  • Requires a TypeSafe API key.
  • Clearing browser storage deletes all saved days.

Getting started

npm ci; cp .env.example .env and set TYPESAFE_API_KEY; npm run dev and open http://localhost:3000.

At a glance

Type
Demo
Status
prototype
Language
TypeScript
Runtime
Next.js, browser
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Mood Pixels is a small mood tracker that uses TypeSafe AI (JEV) to turn a few words about your day into a mood and self-care nudge. Write a check-in and see your mood reflected in a colourful Year in Pixels calendar.

    hellogumbo/awesome-jev

Frequently asked questions

What does Jev decide?

The mood category of your check-in and an energy score from 1 to 5.

Is my text stored?

It is sent for analysis but only the date, mood, score and nudge are saved in your browser.

Does it need a TypeSafe key?

Yes, set TYPESAFE_API_KEY in .env.

Related projects

  • inbox-zero

    Open-source AI email assistant; listed as using Jev as an optional classifier for email intent and triage.

    ProjectproductionTypeScript
  • jev-tab-order

    Chrome extension that groups and orders all tabs in a window by meaning and your rules with a single Jev request.

    ServiceproductionTypeScript
  • orchestkit

    Large Claude Code plugin of skills, agents and hooks that can optionally ask Jev to classify a session's work category.

    ProjectproductionTypeScript
  • SiYuan

    Privacy-first personal knowledge management system, listed as integrating Jev for document classification and tag routing.

    PluginproductionTypeScript
  • docket

    Go terminal app that files documents using five Jev questions: category, sensitivity, urgency, whether action is needed and action state.

    ProjectbetaGo
  • dsh-jev

    DeepSeek Harness plugin that classifies each user message's emotion, urgency and department with Jev and injects it as context.

    PluginbetaTypeScript