How is batching different from one request per issue?

Default packs selected issues plus trimmed project summary into as few requests as fit, one request when limits allow; Advanced forces one request per issue, trading more calls for isolation.

Where do my keys and repo data actually go?

Both keys live in memory only, never localStorage or disk, and vanish on reload; analyses stay in browser IndexedDB, and only api.github.com and the local Jev proxy receive traffic.

Why does it ask for Issues and Contents read-only scopes?

The fine-grained token needs Issues read-only for issues and comments, Contents read-only for README and docs, plus Metadata read-only; classic tokens need repo scope for private repos, which also grants write.

Will Jev or GitHub limits break a large backlog?

GitHub caps unauthenticated loads and skips comments, while Jev charges only input tokens; a typical 200-issue run costs roughly $0.03-0.06, so add a token and batch to stay inside limits.

What are the five things Jev judges per issue?

Complexity, Criticality, Effort and Relevance, plus a fifth speculative Kind that sorts the issue into bug, feature, documentation, question, maintenance or other. All deterministic work such as fetching, trimming, sorting, filtering and exporting stays in code.

Where is my data stored, and what leaves the browser?

Saved analyses live in the browser's IndexedDB under local-issue-classifier, including repository context, issue text, classifications and your filters. The only network traffic is GitHub's api.github.com for the repository you analyse and the local Jev proxy when classifying.

What are the requirements to run it locally?

Node.js 22.13 or newer, pnpm 11, and a Jev API key, with a GitHub token optional. pnpm dev serves a fixed port 5200 with strictPort enabled, and the project is developed with strict TDD.

CommunityJev Models & Reimplementations

Local Issue Classifier

Local-first web app that pulls a repo issues and README, asks Jev to score complexity, criticality, effort and relevance, then sorts and exports.

See highlights

Open github.com

Stars: 0
Language: TypeScript
License: MIT
Published by: Community
Author: JeronimoRepetto
Last verified: Oct 2026

JeronimoRepetto/local-issue-classifier

User repository on GitHub

View on GitHub

Local-first web app that pulls a GitHub repo's issues and README, then asks Jev (TypeSafe AI's decision model) to rate each issue by complexity, criticality, effort and relevance. Filter, dismiss, sort by weighted priority and export as plain text. Keys stay in memory; results stay in your browser.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

Try it: — no install, paste a public repository URL and a Jev key to start. Everything below also runs locally with pnpm dev. Local-first web app that pulls a GitHub repo's issues and README, then asks Jev (TypeSafe AI's decision model) to rate each issue by complexity, criticality, effort and relevance. Filter, dismiss, sort by weighted priority and export as Text, Markdown or HTML. Keys stay in memory; results stay in your browser.

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

Tagscommunity github

Works forJev for Classification

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Batches selected issues into as few Jev requests as fit; one request per issue is optional under Settings Classifier Advanced.
Jev answers Complexity, Criticality, Effort, Relevance plus speculative Kind; deterministic fetch and sorting stay in code.
Keys stay in memory only and vanish on reload; analyses persist in IndexedDB with filters and dismissed state.
Runs at issueclassifier.com with no install or locally via pnpm dev on fixed port 5200; exports Text, Markdown or HTML.

Watch out

Needs a Jev key; without a GitHub token public repos load at 60 requests per hour and comments are skipped. 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

jev-demo

Voice-driven UI prototyper for Next.js: local whisper.cpp transcribes mic audio on the Mac, Jev answers a batch of typed Choice/Noul questions per utterance, and json-render renders the design as shadcn/ui React.

Jev Models & Reimplementations#community#github

Community

julianoczkowski/jev-demoTypeScript

codriver

Per-turn opencode router that asks Jev which fleet model fits the turn, rewriting to that model or falling back on low confidence.

Jev Models & Reimplementations#community#github

Community

johnpozy/codriverTypeScript

Simple-Jev

No-code layer that turns plain English into validated Jev schemas, confirming with chips before deterministic execution and verdict card.

Jev Models & Reimplementations#community#github

Community

ihatecoding01/Simple-JevTypeScript

LocalJev

823

A local Jev-compatible POST /v1/systemone server in TypeScript that maps typed questions onto oMLX classification prompts and normalizes logprob-style answers.

Jev Models & Reimplementations#community#typescript#local

Community

githubnext/localjevTypeScript

OpenJev

174

Express and Vite playground for System One-style decisions, taking a state plus typed questions and returning structured answers. Three swappable backends: per-option LLM micro-scorers, one structured JSON call, or a locally served decider model.

Jev Models & Reimplementations#community#jevbest

Community

SiliconLabAI/OpenJevTypeScript

system-one-foundation-models

Native Swift 6 package that evaluates @Generable structs and enums through System One decision models in 15-150 ms, with on-device Laya, self-hosted laya-serve, and TypeSafe Jev cloud backends.

Jev Models & Reimplementations#community#github

Community

peterfriese/system-one-foundation-modelsSwift

From the Jev guides

Original write-ups on what this entry is for.

Multimodal Decision Models: What Clef and d1 Change

Oct 12, 2026

Jev takes text only; Clef-omni adds image, audio, and video input and Liquid d1 adds images, each keeping the same typed-answer shape. Where that matters, where it does not, and the costs the vendors underplay.

Jev Models & Reimplementations#multimodal#open-models#decision-model

Read article

The Decision-Model Price War

Oct 11, 2026

One model in September, a dozen by October. Clef, Liquid d1, Perplexity, and OpenAI all ship the same typed-answer shape now. How to read the rival benchmarks and pick on your own task.

Jev Models & Reimplementations#decision-model#benchmarks#pricing

Read article

What Is Actually on Hugging Face

Oct 8, 2026

Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.

Jev Models & Reimplementations#open-models#hugging-face#local

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai