jev-rerank-bench

Forty near-identical stacks of legal documents on a concrete floor, one lit in amber — Image from github.com

laguagu/jev-rerank-bench on GitHub

Stars: 0
Forks: 0
Language: TypeScript
License: MIT
Last push: 23 Sep 2026

Read from GitHub on 24 Sep 2026. Counts change daily.

How it uses Jev

  const res = await client.systemOne({
    state: { question, passage: passageState(c) },
    questions: { answers_the_question: noul(RELEVANCE_INSTRUCTIONS, RELEVANCE_CRITERIA) },
  });
  scores.set(c.chunkId, res.answers.answers_the_question.noul);
  inputTokens += res.usage.input_tokens;
  outputTokens += res.usage.output_tokens;
} catch {
  failed++;

View in src/rerank/jev.ts

Open on GitHub

PrimitivesNoul Score

Use casesSemantic reranking

[AINews] Jev: a System One Model that only decides/classifies/routes/scores

AI News daily roundup leading with the Jev launch, summarising RLCD and TypeSafe's 20-200x speed and 40-400x cost claims. Its recap of reactions notes posters using Jev as a structured classifier, judge and routing policy where text generation is unnecessary.

Latent.Space (AI News)Open

ArticleIntent and model routing+1

ModernBERT

Modernized BERT encoder used as the backbone for fast fine-tuned classifiers and rerankers. The non-generative baseline Jev's cost and latency claims are usually measured against. Star count is GitHub's rounded display figure.

AnswerDotAI1.7k starsOpen

AlternativeSupport inbox triage+3

superagents-lab/jev-search

Web search in plain language where Jev chooses sources, time ranges and search terms, then scores each result for relevance, with retrieval through Search1API. Returns links and snippets with visible relevance scores and editable filters, and writes no answers.

superagents-lab446 starsOpen

ProjectSemantic reranking+1

uehaj/jev-semgrep

A grep that matches lines by meaning instead of regular expressions: Jev scores each line against a plain-language description and the tool applies a threshold, combining meanings with AND, OR and NOT.

uehajOpen

134 starsBatch speed <1s/210 lines

ToolSemantic reranking

mrnugget/jev-shell-history

Fish-style autosuggestions for zsh ranked by Jev. As you type, the plugin sends your last 100 distinct history entries and asks which one you are most likely completing, then shows the best match in grey with its score for you to accept.

mrnugget108 starsOpen

ToolSemantic reranking

open-jev: one-pass option scoring with local models

Independent reimplementation inspired by jevlike that scores pre-written options in one batched forward pass by log-probability over a local Gemma 3 4B, shipping an HTTP server, CLI and a TypeSafe System One API implementation.

daseinlabs107 starsOpen

AlternativeIntent and model routing+1

Menu