jsort
Sorts text along a plain-English criterion using pairwise Jev Noul judgments and a locally fitted Bradley–Terry scale, with uncertainty and reliability reporting.
- GitHub stars
- 18 as of 2026-09-22
- Forks
- 0
- Language
- Python
- License
- MIT
- Created
- 2026-09-19
- Last updated on GitHub
- 2026-09-24
- Added to AionEdge
- 2026-09-21

What Jev does in jsort
The project describes itself this way: Sorts text along a plain-English criterion using pairwise Jev Noul judgments and a locally fitted Bradley–Terry scale, with uncertainty and reliability reporting. In the Applications category, Jev typically decides the product's core judgment, such as a document type, a moderation action or a trade direction.
Verification
Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.
Topics
- bradley-terry
- cli
- jev
- openrouter
- pairwise-comparison
- ranking
- sort
- typesafe
How Applications projects use Jev
Complete applications with Jev inside: document classifiers, moderation bots, trading experiments, video tools and more. They show the decision layer embedded in a product rather than demonstrated on its own.
Related Jev projects in Applications
jev-cli (tumf)tumf/jev-cliA CLI and stdio MCP server for typed Jev judgments over text or JSON.★ 12
Python- Jev-Tradeszadescoxp/Jev-TradesA dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.★ 27
Python
refgardenAlbionaHoti/refgardenA visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode.★ 28
TypeScript- jevsqlEugeneBoondock/jevsqlAdds Jev semantic judgments to SQLite for filtering, ranking, matching and tracking decision evidence.★ 5
JavaScript - jev-treereachjalil/jev-treeA hierarchical selector that asks Jev to traverse branches when a catalog has too many options for one question.★ 5
TypeScript - jev-reviewerchoxos/jev-reviewerA systematic-review tool that selects verbatim evidence from papers and supplements for human checking and export.★ 32
JavaScript