Skip to content

Jev directory

Momus Review

A Rust CLI that reviews Git diffs and source scans as fast, staged judgments with concrete evidence, severity and owner routing, powered by TypeSafe Jev through a thin HTTP client speaking the system_one wire format.
Stars
2
Language
Rust
License
MIT
Reading time
3 min
Published by
Community
Author
brianluby
Last verified
Oct 2026

brianluby/momus-review

User repository on GitHub

View on GitHub

Fast, calibrated, staged code & security review (momus)

Forks
0
Last pushed
Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Highlights

  • Two modes, one funnel: momus review reviews the current Git diff and untracked files; momus scan scans every non-ignored source file under a scope.
  • momus github-review posts findings as inline PR comments, at most --max-comments (default 10), best-ranked first; re-runs are idempotent via hidden markers.
  • 0.9.0 is the beta milestone for team testing; real-history calibration and a comparison benchmark remain gates for 1.0.0; merge approval is off by default.
  • The Rust core funnel was validated on OWASP Juice Shop through a golden-set eval harness (momus-eval) with an OWASP-aligned security vocabulary.
  • Flags include --base REV for PR-accurate diffs, --fail-on-blocking for CI, plus --exclude, --follow-ups, --no-refine, --no-cache and --no-redact.

Quickstart

bash
momus review --base origin/main
momus github-review

Watch out

Copy reviewed against the repo README on 2026-10-15; it was truncated inside the github-review section, so the CI setup and later sections were not inspected. The OWASP Juice Shop validation is the project's own golden-set harness; the release notes, offline benchmarks and API docs live in separate files this digest does not cover.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

YouTube: Kubernetes admission control with a decision model, fail-closed.

Hacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.

2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker News

Hacker News: Thread on Selmar's Jev code-review calibration notes and ordering.py comparisons.

Lectem2 pointsCalibrating Jev as a Code ReviewerRead the thread on Hacker News

Hacker News: Jev classifies agent PR hunks as P0, P1, or P2 so reviewers see P0 first.

namanbhulawat47 pointsJev Based Code ReviewRead the thread on Hacker News

From the Jev guides

Original write-ups on what this entry is for.

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai