Skip to content

Jev Mailroom

Mailbox triage proof-of-concept: a local fake IMAP server feeds a listener that asks Jev one batched call per email, and plain Python turns the answers into labels that a single-file dashboard shows.

Stars
3
Language
Python
License
MIT
Published by
Community
Author
selcukusta
Last verified
Oct 2026

About this project

A mailbox triage proof-of-concept. A fake IMAP server feeds a listener, the listener asks Jev one batched call per email, and plain Python turns the answers into labels that a dashboard displays. It only reads and labels mail. Nothing here sends, replies, pays, or moves money. The dashboard, on synthetic demo data. Jev is not a text generator. You send it content plus a set of typed questions, and it returns typed answers with probabilities. Two properties shape this whole design:

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

Highlights

  • Eleven narrow questions go out in one call, and every comparison, threshold and weight stays in Python rather than in the prompt.
  • Two independent axes — kind such as invoice or promotion, and category such as banking or telecom — so one email can land in both.
  • Explicit rules: under 0.60 on kind sends an item to review, and category needs 0.90 or a corroborating question at 0.70, else other.
  • The dashboard is one dependency-free HTML file that polls results.jsonl every two seconds and must be served, not opened as file://.

Watch out

Jev cannot do arithmetic, compare dates, count or write prose, so amounts and due dates are never extracted and attachments are not read — an invoice inside a PDF is judged by its covering email. The README also warns that email content is untrusted input and that a crafted message can move an answer. It is demo-grade: the IMAP stub is plaintext on 127.0.0.1, .mbox and .msg imports are unsupported, and results carry no triage timestamp. 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

51GitHub stars
Local LinkedIn recruiting workspace on Browser Use's Jev Ultrafast: Jev screens titles, drives navigation, and assesses profile excerpts against your brief while a live browser stays visible; matches and evidence export as JSON.
Jev Agents & MCP#community#jevbest#catalog-import
33GitHub stars
Codex Skill plus stdlib-only Python CLI that recommends which installed skill to read next for a task, allowing no-skill or uncertain answers and never executing candidates.
Jev Agents & MCP#community#jevbest#catalog-import
72GitHub stars
MCP server over stdio that gives coding agents fourteen Jev judgment tools, turning evidence plus an enumerable question into auto, review, or escalate actions from calibrated probabilities.
Jev Agents & MCP#community#jevbest#catalog-import
Research runtime that pages a large logical tool and context space through a small bounded Jev decision surface with explicit approvals.
Jev Agents & MCP#community#jevbest#catalog-import
25GitHub stars
Agent-oriented playbook for using Jev as a cheap, fast decision layer that triages, classifies, scores, and gates work before expensive browser, research, retry, or subagent steps.
Jev Agents & MCP#community#awesomejev#catalog-import
23GitHub stars
Coding-agent plugin that routes prompt classification, subagent tiering, edit rule checks, and fast Jev-backed compaction through small typed judgments.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai