egma-ai/jev-code-reviewer
Review behavior, not just diffs. Jev prioritizes human attention; OpenAI explains the changes. Local CLI + agent skill + GitHub extension.
About the project
A local CLI and Chrome extension for reviewing PRs made by coding agents: changes are classified as P0/P1/P2 and diffs are explained in natural language via OpenAI.
Useful for
- Run jev-reviewer analyze on your agent's PR to see only P0 changes
- Tune priorities via .jev-reviewer.json for a specific repository's rules
- Enable the extension on the Files changed page to read logic instead of code
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 41 stars so far today, about 65 expected by the end of the day.
- The repository is 6 days old and already has 39 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Jev Based Code Review” — 34 points, 5 h ago.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 39
- Today
- 41 · ≈ 65 by evening
- Forks
- 0
- Issues and pull requests
- 2
- Watchers
- 0
- Language
- JavaScript
- License
- MIT
- Created
- September 19, 2026
- Last push
- September 25, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Jev Based Code Review34 points, September 25, 2026
Spotted in
- September 25, 2026Spotted on Hacker News
Similar by description
-
0.0
devagrawal09/stanley-code
CLI tool for checking and understanding code changes: routes natural-language requests to deterministic workflows instead of starting a general agent. Requires Node.js 22.18+, git, and a TypeSafe API key.
-
1.9
github/github-mcp-server
GitHub's official MCP server that connects AI tools directly to GitHub's platform. It lets agents and assistants read repositories, manage issues and PRs, analyze code, and automate workflows through natural language.
-
3.1
jerryjliu/docjev
Python library, CLI, and local app for classifying documents into categories and splitting PDF/DOCX/PPTX packets into separate documents using natural-language rules.