zsh history completion with Jev
X demo of zsh completion where Jev picks the most likely next command from the last 100 deduplicated history entries.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This X post by DIYgod shows a zsh completion trick using Jev. According to the list summary, it takes the last 100 deduplicated shell history entries, asks Jev which is the most likely next command, and shows it greyed out after the prompt as a suggestion.
It is a small, practical example of using a Choice question over a user's own data to drive an interface.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which of the last 100 history commands is most likely next? | — |
How it works
- Collect the last 100 unique history entries.
- Ask Jev which is most likely next.
- Show it as a greyed-out suggestion.
Strengths
- Simple, useful developer-experience demo.
Caveats
- Social post; no code linked.
- Sends shell history to a hosted model.
At a glance
- Type
- Discussion
- Status
- discussion
- Runtime
- zsh
Use cases and integrations
How curated lists describe it
X: picks the most likely next command from the last 100 deduplicated history entries by asking Jev, and shows it greyed out after the prompt.
yibie/awesome-jev
Frequently asked questions
What does Jev decide?
Which recent history command you are most likely to run next.
How many commands are considered?
The last 100 deduplicated entries.
Is there a privacy concern?
Yes, shell history is sent to the hosted model.
Related projects
One text box that morphs into the right UI card as you type, with Jev answering 14 typed questions per input and code doing the maths.
DemoprototypeTypeScriptLocal natural-language task workspace where Jev, OpenAI or Gemini turn requests into view and task changes, with speed and cost comparisons.
AppprototypeTypeScriptWeb app for yes/no life decisions: ask Jev for a probability of yes, flip a fair coin, or both, inspired by a coin-toss study.
ProjectprototypeJavaScriptSource for a shared emoji canvas where Jev picks the next emoji and its placement after every stroke and judges if the shape is unfinished.
ProjectproductionTypeScriptIDE and browser extensions to find and install agent Skills and Subagents, with an opt-in Jev check when local detection can't decide.
Browser extensionproductionTypeScriptOpen-source AI email assistant; listed as using Jev as an optional classifier for email intent and triage.
ProjectproductionTypeScript