Built with Search and retrieval

jevbox

A full stack, permission-aware document library. Browse with Extend UI Finder, inspect document trees and parsed output, share with organization members, search the hierarchy with

754 ★ on GitHub

What it is

A full stack, permission-aware document library. Browse with Extend UI Finder, inspect document trees and parsed output, share with organization members, search the hierarchy with JEV, and ask source-grounded questions through the AI SDK.

What the README says it does

  • Better Auth email/password authentication with mailbox verification, password recovery, and signed HttpOnly session cookies.
  • Nested categories and uploads up to 30 MB, durable indexing jobs, retries, and persistent document content.
  • Select documents and choose Organize to queue classification, with durable progress and failures visible in the library. Existing paths are preferred; new branches are proposed and validated when needed.
  • Fixed icon rail, Jevbox identity, Nucleo icons, compact breadcrumbs, and light/dark themes with Retina hairlines.
  • Extend UI Finder and PDF, DOCX, XLSX, and PPTX viewers, with Base UI and coss primitives.

From the project’s README.

Where the decision sits

jevbox calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev.

How active it is

Created 2026-09-29, last pushed 2026-10-31, 754 stars and 87 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.

Find out what your data actually supports

We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.