inbox-zero
Open-source AI email assistant; listed as using Jev as an optional classifier for email intent and triage.
Overview
Inbox Zero is a widely used open-source AI email assistant. It organizes the inbox, pre-drafts replies in the user's tone, manages calendar briefings, files attachments to Drive or OneDrive, blocks cold email, bulk-unsubscribes and archives, and can be driven from Slack or Telegram. Users write rules in plain English to say how the assistant should handle mail. It is available hosted or self-hosted via a CLI with Docker.
Two directory lists describe Jev as an optional classifier backend in Inbox Zero, returning bounded categories and yes/no probabilities to classify incoming email intent and triage action items. The fetched README does not mention Jev or TypeSafe, so the scope of that integration (which rules use it, how it is configured, and whether it is merged or experimental) should be checked in the code or docs.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which category or intent does this incoming email belong to?(inferred) | — |
| Yes / no | Does this email require an action or reply?(inferred) | yes · no |
How it works
- Email arrives in the connected inbox
- Classifier (optionally Jev) assigns a category and yes/no flags
- User-defined plain-English rules decide labels, archiving or drafts
- Assistant drafts replies or files items accordingly
Strengths
- Bounded categories and probabilities instead of free-text classification, per the lists
- Mature product with hosted and self-hosted options
Caveats
- README does not mention Jev; integration details unverified
- Jev appears to be optional rather than the default classifier
Getting started
`npx @inbox-zero/cli setup` then `npx @inbox-zero/cli start` (Docker and Node 24+), and open http://localhost:3000.At a glance
- Type
- Project
- Status
- production
- Language
- TypeScript
- Runtime
- Next.js web app
- Has code
- yes
Use cases and integrations
How curated lists describe it
Email productivity: open-source AI email assistant that uses TypeSafe Jev System One decision models to classify incoming email intent and triage action items.
yibie/awesome-jevEmail assistant where Jev is an optional classifier backend returning bounded categories and yes/no probabilities.
cobanov/awesome-jev
Frequently asked questions
What would Jev decide in Inbox Zero?
According to the lists, the intent or category of incoming email and yes/no triage questions.
Is Jev required?
No, the lists describe it as an optional classifier backend.
Can I self-host it?
Yes, with the @inbox-zero/cli setup and start commands.
Related projects
Hermes Desktop plugin where Jev maps misspelled, shortened or meaning-based slash commands to real ones at ≥0.85 confidence.
PluginbetaJavaScriptTriage for DingTalk mail and chats where Jev sorts messages into needs-reply, updates, promo, sales or spam with attention flags.
ProjectbetaPythonGoogle Apps Script that labels, archives or trashes Gmail conversations based on Jev answers to your plain-English yes/no questions.
ProjectbetaJavaScriptGmail classifier running on Google Apps Script where Jev decides action-needed, importance and category for each thread.
ProjectbetaTypeScriptAndroid and Windows message-priority assistant where Jev scores urgency and reply-now for each message and sorts them by colour.
ProjectbetaKotlinLocal-first work-message classifier that uses Jev to sort chat messages into urgent, to-do, worth reading and skip, with cross-chat to-dos.
ProjectbetaJavaScript