Awesome Jev / Data & Search

Data & Search

Search intent classification, query routing, vector re-ranking, and ETL triage.

Back to All Projects17 reviewed repositories
pg-jev repository icon by realZachi

realZachi

pg-jev

179
Data & SearchPostgreSQLShell

Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.

What Jev does here

Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.

Combines semantic conditions with existing SQL and reuses cached results.

#database-vector#classification-ranking
103 evidence links
Inspect details
jev-search repository icon by superagents-lab

superagents-lab

jev-search

146
Data & SearchMITTypeScript

Searches the web with Jev choosing sources and time ranges, then ranking returned links.

What Jev does here

Judges search intent, source and time settings, and relevance of individual results.

Keeps links, snippets, editable filters and source-failure warnings visible.

#search-retrieval#classification-ranking
222 evidence links
Inspect details
llama-index-jev repository icon by WiktorB2004

WiktorB2004

llama-index-jev

2
Data & SearchMITPython

Provides Jev rerankers and routers for LlamaIndex to score retrieved passages or select query tools.

What Jev does here

Uses Score for passage relevance and Choice for selecting query engines or tools.

Adds Jev judgments to existing retrieval and query workflows.

#search-retrieval#classification-ranking#llm-routing-cost
2 evidence links
Inspect details
Data & SearchMITJavaScript

A Jev project directory and discovery pipeline that stores integration evidence and can use Jev for classification.

What Jev does here

When configured with a key, sends project state and candidate categories to Jev; otherwise uses local classification rules.

Keeps a project index alongside concrete source evidence.

#search-retrieval#classification-ranking
2 evidence links
Inspect details
jev-curate repository icon by AkashPriyadarshii

AkashPriyadarshii

jev-curate

3
Data & SearchMITRust

A Rust dataset-filtering experiment using Jev scores to keep or reject text records.

What Jev does here

Runs local prefilters, calls TypeSafe and applies probability and score thresholds to each record.

Provides local prefilters and score thresholds for experimenting with per-record data pipelines.

#classification-ranking#evaluation-benchmarks
5 evidence links
Inspect details
jevql repository icon by kylemclaren

kylemclaren

jevql

3
Data & SearchMITGo

Adds Jev semantic filtering, grouping, and ranking around ordinary PostgreSQL without installing a database extension.

What Jev does here

The CLI or service layer evaluates jev_* calls over row text before completing the query.

Shares semantic SQL interfaces across a CLI, HTTP, MCP, and SDKs.

#database-vector#classification-ranking
2 evidence links
Inspect details
jev-scout repository icon by AkashPriyadarshii

AkashPriyadarshii

jev-scout

1
Data & SearchMITRust

A repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.

What Jev does here

Compares candidate information with the request, scores fit and maintenance signals, and chooses a candidate.

Keeps recommendations tied to retrieved candidates and source links.

#search-retrieval#classification-ranking#cli-git-gates
2 evidence links
Inspect details
pg_typesafe repository icon by giuliosmall

giuliosmall

pg_typesafe

76
Data & SearchMITC

A pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.

What Jev does here

Converts SQL input into System One requests and returns answers through database functions.

Adds typed semantic judgments to existing database queries.

#database-vector#classification-ranking
2 evidence links
Inspect details
duckdb-jev repository icon by colliber

colliber

duckdb-jev

8
Data & SearchMITC++

A DuckDB extension that calls Jev from SQL and returns answers as ENUM, numeric, or STRUCT types.

What Jev does here

Asks Choice, Score, and Noul questions about row text and maps answers to SQL types defined by the questions.

Uses structured judgments while querying tables or Parquet data.

#database-vector#typed-decisions
2 evidence links
Inspect details
jevsql repository icon by EugeneBoondock

EugeneBoondock

jevsql

3
Data & SearchMITJavaScript

Adds Jev semantic judgments to SQLite for filtering, ranking, matching and tracking decision evidence.

What Jev does here

Sends row data and typed questions to Jev and maps answers into queryable SQL results.

Provides batching, caching, budgets and decision history.

#database-vector#search-retrieval#classification-ranking
12 evidence links
Inspect details
Data & SearchApache-2.0Python

A Python reranker that packs a query and up to 30 candidates into one Jev state, with one Noul relevance question per document.

What Jev does here

One Noul relevance question per document; long lists are chunked and scored, then filtered by threshold or sorted.

Uses a probability as a threshold or sort key instead of a generative reranker.

#search-retrieval#classification-ranking
4 evidence links
Inspect details
Data & SearchMITPython

Retrieval evaluation system measuring Jev reranking against lexical, embedding, and fusion baselines across 9,831 query-document pairs.

What Jev does here

Invokes Jev judges to grade multi-level relevance on bilingual queries, evaluating ranking metrics and judge-circularity effects.

Provides rigorous empirical evidence comparing discrete judgment rerankers against vector search in multilingual discovery contexts.

#search-retrieval#evaluation-benchmarks#classification-ranking
8 evidence links
Inspect details
polar_llama repository icon by pnthn-ai

pnthn-ai

polar_llama

30
Data & SearchMITTypeScript

A Polars library for parallel provider inference that also calls Jev per row as Noul, Choice, and Score questions, or as one typed contract over a document.

What Jev does here

One System One request per row: Noul, Choice, or Score answers land as ordinary typed columns with confidences.

Puts closed-set Jev answers on existing Polars columns instead of another chat-completion pass.

#search-retrieval#classification-ranking
22 evidence links
Inspect details
Data & SearchMITJavaScript

A semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.

What Jev does here

Batches about thirty lines and asks jev-latest a Score or Noul per line for the stated meaning.

A zero-runtime-dependency semantic grep; query text is sent to TypeSafe.

#search-retrieval#cli-git-gates#typed-decisions
24 evidence links
Inspect details
kody repository icon by kentcdodds

kentcdodds

kody

654
Data & SearchFSL-1.1-ALv2TypeScript

Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.

What Jev does here

Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.

Attaches Jev rerank to existing MCP search instead of replacing retrieval. License is Fair Source FSL-1.1-ALv2, not OSI open source.

#search-retrieval#mcp-integrations#classification-ranking
653 evidence links
Inspect details
every repository icon by sufianetaouil

sufianetaouil

every

3
Data & SearchMITTypeScript

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.

What Jev does here

Converts natural language questions into boolean/probability queries across functions, ranking matches locally by confidence.

Enables natural language function discovery across codebases at low cost, similar to an intelligent grep.

#search-retrieval#classification-ranking
2 evidence links
Inspect details
jev-bfs repository icon by komikat

komikat

jev-bfs

0
Data & SearchMITTypeScript

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

What Jev does here

Applies Jev semantic heuristic scoring and pruning to outbound links at each BFS exploration step.

Combines classic graph traversal with probabilistic judgments to prune the Wikipedia multi-hop search space.

#search-retrieval#classification-ranking
5 evidence links
Inspect details

Explore Other Architecture Categories

Explore Jev Decision Workflows