データ・検索

52 · 各項目の確認根拠をご覧ください。掲載は独立した実行検証を意味しません。

• pg-jev

  realZachi · データ・検索

  PostgreSQL の行を自然言語で絞り込み、分類、順位付けする。

• jev-search

  superagents-lab · データ・検索

  Jev が検索元と期間を選び、取得したウェブリンクを並べ替える検索ツール。

• llama-index-jev

  WiktorB2004 · データ・検索

  LlamaIndex 向けに、検索文章の採点と問い合わせ先の選択を行う Jev 部品を提供する。

• jevsome-projects

  ozers · データ・検索

  接続の根拠を保存し、任意で Jev に分類させるプロジェクト一覧と探索パイプライン。

• jev-curate

  AkashPriyadarshii · データ・検索

  Jev の採点でテキストレコードを採用・除外する Rust のデータセット選別実験。

• jevql

  kylemclaren · データ・検索

  データベース拡張を入れずに、通常の PostgreSQL へ Jev による絞り込み、分類、順位付けを加える。

• jev-scout

  AkashPriyadarshii · データ・検索

  検索で得たリポジトリーと Rust crate の候補を、Jev が依頼に合わせて評価・選択する。

• pg_typesafe

  giuliosmall · データ・検索

  SQL から Jev の分類、二択、採点を呼び出す pre-alpha の PostgreSQL C 拡張。

• duckdb-jev

  colliber · データ・検索

  SQL から Jev を呼び、ENUM、数値、STRUCT などで答えを返す DuckDB 拡張。

• jevsql

  EugeneBoondock · データ・検索

  SQLite に Jev の意味判断を加え、絞り込み、順位付け、照合と根拠追跡を行う。

• reranker

  hev · データ・検索

  クエリと最大約 30 件の候補を 1 つの Jev state に入れ、文書ごとに Noul「関連するか」を問い、フィルタまたはリランクに使う。

• jev-search-rerank-eval

  zhuyansen · データ・検索

  9,831 件のペアと 164 件の日英クエリを用いて、Jev リランクと単語検索、ベクトル検索、ハイブリッド検索を比較検証する評価システムです。

• polar_llama

  pnthn-ai · データ・検索

  Polars 上の並列推論ライブラリ。チャットモデルは各社の補完 API を使い、Jev は行ごとに Noul、Choice、Score、または文書全体に型付き契約を当てる。

• jev-semgrep

  uehaj · データ・検索

  各行が意味に合うかを Jev で採点する grep。AND/OR/NOT と言語をまたいだ検索ができる。

• kody

  kentcdodds · データ・検索

  任意の二段検索。ハイブリッド候補を広げたあと、Workers AI の typesafe/jev Score で並べ替える。

• every

  sufianetaouil · データ・検索

  Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.

• jev-bfs

  komikat · データ・検索

  Wikipedia link race pathfinder guided by Jev: assesses outbound links to navigate between two articles in real time.

• jselect

  keltokhy · データ・検索

  Selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection.

• JevFind

  Peu77 · データ・検索

  Fast semantic code search powered by Jev. Find the relevant files, line ranges, and snippets

• jlink

  keltokhy · データ・検索

  The string baselines are best-match Jaro-Winkler and best-match TF-IDF cosine; the table shows the better of the two. Exact matching after normalization scores 0.26, 0.41, 0.00, 0.00 and 0.22.

• jev-search

  larguesa · データ・検索

  Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.

• jeveryword

  jkrup · データ・検索

  Jev answers multiple-choice questions and does not generate text, so on its own it cannot return a name, an email address or a quote. jeveryword numbers the words of your text, offers those numbers as the answer options, and converts the numbers Jev picks back into the original substring with its character offsets.

• jev-311-heatmap

  CompleteTech-LLC-AI-Research · データ・検索

  The live run excluded 205 reports with missing or invalid coordinates, completed **634 API calls without retries**, and reported **539,979 input tokens**. Repeated descriptions share one evaluation.

• hfjev

  hemanth · データ・検索

  Classify Hugging Face datasets across typed semantic dimensions with TypeSafe Jev System One. Auto-adapts evaluation rubrics to dataset domains (reviews, news, LLM tuning, support) and classifies rows in a single parallel System One call with calibrated probabilities.

• jev-in-codex

  teempai · データ・検索

  Jev-powered tool and skill selection, context search, and output triage for Codex via MCP

• jev-reranker

  shinpr · データ・検索

  Rerank, filter, and compress JSON search results with TypeSafe AI's Jev.

• jevframe

  ktaletsk · データ・検索

  Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.

• jev-information-extraction

  abhishekmamdapure · データ・検索

  Ask questions about a PDF. Use Jev to rank the source text that answers them. Inspect each match, its probability, and its location on the original page.

• vector-graph-rag

  zilliztech · データ・検索

  Milvus-based multi-hop retrieval library with two-stage Jev relation selection and full-passage reranking, achieving 86.07% average Recall@5 on MuSiQue and 2Wiki.

• memsearch

  zilliztech · データ・検索

  A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

• GPTCache

  zilliztech · データ・検索

  Semantic cache with a Jev evaluator that uses Noul judgments to check whether a cached response can serve an incoming request.

• deep-searcher

  zilliztech · データ・検索

  Open Source Deep Research alternative with Jev search-stopping evaluation.

• bootcamp

  milvus-io · データ・検索

  Runnable search tutorials using Gemini embeddings, Milvus retrieval, and Jev judgments for reranking, filtering, and routing.

• jev-papers

  stas4000 · データ・検索

  1,000 arXiv AI papers classified with one Jev decision each, checked against an LLM judge. Open rebuild, MIT.

• jev-bigquery-cloudrun

  jeffonelson · データ・検索

  Classify support tickets in BigQuery with Jev and Cloud Run

• jev-research-pipeline

  shimo4228 · データ・検索

  **Code owns the loop, Jev judges, Qwen writes: a daily research monitor for standing questions.**

• jev-dataops

  RenaGao · データ・検索

  An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.

• jevsql

  sarathi-aiml · データ・検索

  Text-to-SQL where the model never writes SQL — typed, calibrated decisions (TypeSafe Jev) + code-assembled queries

• jevpdf

  kylemclaren · データ・検索

  `server/index.ts` is a small Bun server that serves `dist/` and the `/api/jev` proxy, which uses the same forwarding code as dev (`server/jev-upstream.ts`). Because the live proxy spends real credits, it only accepts same-origin POSTs from the app, pins the model, caps request size, and rate-limits each IP.

• jev-retrieval

  romeromarcelo · データ・検索

  Grep-shaped Rust CLI for coding agents that finds files matching a plain-language concept: a local BM25 pass recalls candidates, Jev verifies each file window-by-window with Noul gates, and one listwise Choice per lane reranks the kept files into `path:line score` output with calibrated probabilities. (Author-submitted: I am the maintainer.)

• duckdb-jev

  prasanthj · データ・検索

  High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL.

• DataJev

  zzz1YAO · データ・検索

  ⚡ DataJev LLM → Analyze Jev → Continue / Switch / Verify / Stop System-1 control for System-2 data agents

• milvus-model

  milvus-io · データ・検索

  A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

• laya-jev-GraphRAG

  bodepudimuneendra-netizen · データ・検索

  Agentic GraphRAG engine using swappable System One decision models (local Laya / cloud Jev). Features a complete 4-phase pipeline (Ingestion, Pre-Retrieval, Traversal, Post-Retrieval) and evaluation across Neo4j, Memgraph, Apache AGE, and Kùzu driven by a custom A* traversal algorithm.

• sieve

  nothans · データ・検索

  Sieve checks a folder of Markdown notes against itself. Crosscheck compares every note with every other, from both sides, and lists the pairs that contradict each other, the pairs that make the same point twice, and the notes that have gone stale. It also ranks the whole folder by any plain-English question, and lints notes against plain-English rules in CI. No index, no embeddings, no generated text. Node, no dependencies.

• jev-rag

  aifabrice · データ・検索

  Local knowledge search with three modes: BM25 + Jev by default, agentic multi-query lexical search + Jev without vectors, and optional BM25 + embeddings/RRF + Jev, with grounded streaming answers.

• jev-reviews

  halfspin-qc · データ・検索

  The flagship experiment in this workspace is **`jev-reviews`**: an automated pipeline that ingests Google Maps restaurant reviews from **Apify Storage**, stores and deduplicates them in **Supabase PostgreSQL**, and classifies them using **Jev (TypeSafe System One)** or traditional generative LLMs across 5 operational pillars, extracting dishes, customer highlights, and owner recommendations.

• jevtok-ts

  aarzhaev · データ・検索

  **No Python, network calls, API keys, native extensions, or runtime dependencies.** Vocabulary and lookup tables ship inside the package. Ordinary `o200k_base` tokenization is not interchangeable with Jev: `evidence` is three tokens and `2024` is four.

• jev-harness

  PromtEngineer · データ・検索

  A Pi agent harness built around TypeSafe's Jev (System One model): router, context picker, gate, verifier. Tested on Neon Postgres branches.

• JevDeepResearch

  sunyasheng · データ・検索

  GPT directs the research; Jev uses Choice and Noul to locate evidence across document regions concurrently, and code returns original passages for GPT to verify and continue. The released integration pairs Pi-Serini BM25 search with Jev batches of 20, 40, or 60 documents.

• el-jev

  vijaycinn · データ・検索

  High-speed System One decision sidecar & Copilot CLI pre-turn hook powered by Azure AI Foundry Cohere with keyless Entra ID auth.

• jev4pg

  Sheltercosmo · データ・検索

  Semantic querying and gate decisions in PostgreSQL powered by Jev Noul predicates.