docket
Go terminal app that files documents using five Jev questions: category, sensitivity, urgency, whether action is needed and action state.
Overview
Docket is a Go terminal document classifier. It copies a document into a local library, extracts its text, asks Jev for typed decisions and files the copy without moving or editing the original. Every document gets five questions: a Choice for the primary category, a Score for sensitivity (0 to 3), a Score for urgency (0 to 3), a Noul for whether the recipient must act, and a Choice for whether an action is outstanding, completed, quoted, absent or unclear.
Deterministic Go logic wraps the results: explicit thresholds flag uncertain categories and actions separately, scores become practical labels such as Personal or Time-sensitive, and code chooses the next step and the filing destination. In the TUI you can mark actions done, not applicable or reopened. Jev's raw outputs stay visible alongside Docket's guidance.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | What is the document's primary category? | — |
| Score | How sensitive is its information? | 0 · 1 · 2 · 3 |
| Score | How urgently must the recipient respond? | 0 · 1 · 2 · 3 |
| Yes / no | Does the document require the recipient to act? | yes · no |
How it works
- Copy the document into the local library and extract text
- Ask Jev five typed questions
- Go code applies thresholds and maps scores to labels
- File the copy and show guidance; user tracks action state in the TUI
Strengths
- Never modifies the source document
- Separate uncertainty flags for category and action
- Transparent Jev outputs alongside guidance
Caveats
- Document text is sent to TypeSafe
- Personal tool; early roadmap
Getting started
See the README and website (docket.glamboyosa.xyz) for installation; set TYPESAFE_API_KEY.At a glance
- Type
- Project
- Status
- beta
- Language
- Go
- Runtime
- terminal UI
- Has code
- yes
Use cases and integrations
How curated lists describe it
A Go TUI that uses Jev to classify documents, assess sensitivity and urgency…
wh000wh000/awesome-jev-live
Frequently asked questions
What does Docket ask Jev?
Category, sensitivity, urgency, whether action is needed and the action's state.
Does it move my files?
No, it files a copy and never edits the source.
Who decides the filing location?
Deterministic Go logic using Jev's answers and thresholds.
Related projects
Privacy-first personal knowledge management system, listed as integrating Jev for document classification and tag routing.
PluginproductionTypeScriptObsidian plugin that ranks existing vault folders and tags for the active note with Jev and only moves or tags after you confirm.
ProjectbetaTypeScriptLLM-maintained Markdown wiki where a System One classifier decides where documents and questions go, keeping it fast as it grows.
ServicebetaPythonDocker service that classifies the Paperless-ngx inbox with Jev (or local Clef via Ollama), setting confident fields and queueing the rest.
ProjectbetamacOS menu-bar link router that opens each link in the right browser profile, asking Jev when no local rule matches and learning rules.
ProjectbetaSwiftCLI that classifies documents with a Jev Choice and moves them into category folders, with a pluggable backend for local models.
ProjectbetaPython