Egma-ai releases Jev code reviewer for local AI PR classification
Jev Code Reviewer is an open‑source tool that lets developers inspect pull requests generated by coding agents without sending any data to external services. It classifies each file change into three priority levels—P0, P1 and P2—and displays only P0 changes by default, letting users expand lower‑priority sections as needed. The diffs are also rendered in natural‑language explanations, and the…
Key points
- Jev reviewer classifies PR changes into P0‑P2, showing only P0 by default
- Runs locally on Node.js 22+, no code is sent to GitHub or external servers
- Analyzes first 12 diff hunks by default, configurable up to 100 with --max‑units
The reviewer runs entirely on a local machine that meets the Node.js 22+ requirement. After cloning the GitHub repository (egma‑ai/jev-code-reviewer) and installing dependencies, users start a local server and connect a Chrome extension to it. The extension communicates solely with the local server at 127.0.0.1:4731. By default it analyzes the first 12 change units (diff hunks) in path order, but the --max‑units flag can raise the limit to 100. Keys for OpenAI and TypeSafe are stored locally in an owner‑only file, not encrypted, and can be replaced via a provided script.
Jev’s design aims to reduce the mental burden of reviewing large, AI‑generated PRs, offering configurable priority policies and ensuring that no code leaves the developer’s environment unless explicitly sent to the chosen AI providers.
Jev Based Code Review
github.com · 19 September 2026Loading the full article…
This text was published by github.com. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
1source- Hacker News discussion · 41 pointsnews.ycombinator.com
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Claude Tag now supports personal connectors in channels · 1 src
- OpenAI gives free access to Daybreak and GPT-5.6 Sol to Ukraine · 5 src
- Opinion: exploring AI‑IR, an intermediate language for ChatGPT and Grok · 2 src
- Meta's AI agent Muse draws 500,000 users in its first week · 5 src
- Claude Opus 5.5 outperforms ChatGPT-6 in four of five tests · 1 src
Comments
via GitHub Discussions