openqodex
by openqodex
OpenQodex is a command-line tool that reviews the code changes your AI coding agent has written before you push them. It runs security scanners, then uses separate Claude Code or Codex sessions to check each finding and produce a report.
- Stars
- 1k +39 a day, est.
- Licence
- Apache-2.0
- Runs on
- Your computer
- Setup
- Moderate
- Language
- TypeScript
- Age
- 26 days
What you can do with it
- Review uncommitted and unpushed changes from Claude Code, Codex, Cursor or Cline with one command
- Scan changes for leaked secrets and known vulnerable dependencies, and get HTML, Markdown and SARIF reports
- Block or warn on pushes with a git pre-push hook or a GitHub Action on pull requests
Make money with it
A freelance developer could offer AI-assisted code delivery with a documented review report attached to each change as a quality and security assurance.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Catch bugs, leaked secrets and vulnerable dependencies in AI-written code before it ships, reducing costly fixes later
- Add automated review to pull requests in a small team without paying for a hosted review service
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Run `npx openqodex init` in a terminal with Node 22 or newer and git; it sets up your agent and downloads the scanners your repository needs.
Follow the official instructions in the project README.
Things to check
- Full review needs Claude Code or Codex installed and logged in, which may need a paid subscription
- The GitHub Action full review needs an Anthropic API key
- macOS and Linux only; not tested on Windows or WSL
- The reviewer sends your change to the model provider of your login
- Cursor and Cline cannot act as the reviewer and have no push gate
Who's talking about it
Checked 28 Oct 2026. Summary drafted by AI from the project's README.
