Skip to content

Jev directory

Gallant

A customizable linter that asks decision models like Jev and Clef your fuzzy rules — does the comments in this file repeat what the code says? — in a single Go binary with no runtime and minimal dependencies.
Stars
4
Language
Go
License
MIT
Reading time
3 min
Published by
Community
Author
madxmike
Last verified
Oct 2026

madxmike/gallant

User repository on GitHub

View on GitHub

Gallant is a customizable linter built to utilize Decision Models (i.e. Jev, Clef, and other system one models) to lint your code, documents, and any other text-based files.

Forks
1
Last pushed
Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Languages
Go
Platforms
CLI
Capabilities
Open sourceRequires API key

Highlights

  • Lints code, documents and other text-based files by asking a decision model fuzzy rules that deterministic systems handle badly.
  • The README's example rule: does the comments in this file repeat what the code already says.
  • No runtime: go install github.com/madxmike/gallant/cmd/gallant@latest, or pin a release such as @v0.1.0.
  • Looks in the relative .agents/gallant folder for rules by default; gallant . applies them to all files under the relative path.
  • Hand-rolled parsers for rule frontmatter, diff splitting and the error-body snippet ship with fuzz targets runnable via go test ./rules -fuzz.

Quickstart

bash
go install github.com/madxmike/gallant/cmd/gallant@latest
gallant .

Watch out

Copy reviewed against the repo README on 2026-10-15; the captured README was truncated inside the privacy section. The README warns decision models have small context windows — orders of a couple hundred to a couple thousand tokens — and that large files will be rejected. The author's comparison to other tools is a stated personal opinion.

Questions about this entry

Short answers drawn from the linked project or page.

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