reposource-backed
Jev Search
Jev chooses sources and query settings, then re-ranks results returned by search engines. It does not generate an answer.
MANY ITEMS, FEW DECISIONS
Search, ranking & queues
Thousands of pages, mentions, emails, ads or candidates screened by parallel yes/no and score questions before anything expensive runs.
From this task to a first run
Choose a project, read its requirements, then follow its setup reference or a related guide.
- Jev Search: How to run →
Node.js 22.12+, pnpm 10.8.0 and a Cloudflare login
- MemSearch: Jev memory reranking: How to run →
Python environment with pip; a folder of Markdown notes
- GPT Researcher: Jev context selection: How to run →
Python 3.12+ and pip
Try a walkthrough
- Select relevant context with Jev →
Score a small shortlist of passages, preserve their source IDs and pass selected evidence to your answering model.
Re-rankers, relevance gates and retrieval fusions with per-item costs from each author.
79 entries
demoauthor demo
8,790 SEO decisions
Hundreds of pages are screened for internal-link fit through thousands of yes/no decisions.
demoauthor demo
Buying-signal ranking at social scale
A pipeline ranks social mentions by intent, fit, competitor context and reach.
demoauthor demo
400-company candidate matching
One profile is scored for fit, chance, confidence and mismatches across 400 companies.
postauthor demo
Put Jev in front of an expensive queue
Business ideas around quotes, leads, support, clipping, applications, marketplaces and browser agents.
demoauthor demo
Ad creative evaluation
Parallel judgments score advertising creative against a fixed rubric.
demoauthor demo
Analyzing an X archive
Jev classifies and scores a creator's own posting history across several criteria.
benchmarkauthor demo
Email classification speed test
A visual comparison places Jev next to Luna, Sonnet and Flash on email classification.
reposource-backed
pg-jev
A PostgreSQL extension that exposes Jev-backed categorical judgments over table rows.
integrationsource-backed
LlamaIndex reranker and selectors for Jev
Two PyPI packages: a `JevRerank` postprocessor using Score and single/multi selectors using Choice for LlamaIndex routing.
demosource-backed
neo4jev: graph navigation with Jev
Outgoing relationships become choices, Jev returns next-hop probabilities, and a beam search walks the graph; shipped as a library, notebooks and a Streamlit app on Neo4j's public Companies knowledge graph.
reposource-backed
blink: codebase search with Jev-scored paths
Jev scores file and folder names so an ensemble of walkers is allocated across the most probable paths; a Bun CLI with recursive and multi-walker modes and JSON traces.
demoauthor demo
DuckDB extension classifying rows with Jev
A DuckDB extension that calls Jev to classify rows of any CSV, Parquet file or table from SQL.
demoauthor demo
500 emails classified for 3.5 cents
A video demo classifying 500 emails in seconds.
demoauthor demo
Email classification on 1,500 real emails
An early video demo running Jev over 1,500 of the author's own emails.
benchmarkauthor demo
Near Here: Jev vs Mistral vs Gemini on event validation
A UK events platform compared three models on approving or rejecting 50 real listings (venue hire, products and cancelled events filtered out), publishing the cases as a PDF.
articleauthor demo
Every: Jev judged everything I've written in 0.7 seconds
An early-access test in which the author had Jev score his own writing corpus; widely cited by other write-ups as the first non-TypeSafe measurement.
postauthor demo
Zero-shot Jev vs an internal fine-tuned classifier
A team pointed Jev at a private benchmark and reports it came within a few recall points of their fine-tuned Qwen at matched precision, while the fine-tune remains faster and has not been replaced.
demoauthor demo
TypeSafe Typewriter on Val Town
A playable demo that runs 16 typed judgments on your text (tone, urgency, AI-written detection and more) on every keystroke with a single API call.
integrationsource-backed
pg_typesafe: Jev from SQL (C extension)
A pre-alpha PostgreSQL C extension exposing typesafe_noul(), typesafe_classify(), typesafe_score() and batched variants that call the API from SQL.
integrationsource-backed
duckdb-jev
A DuckDB extension with jev_choice(), jev_score(), jev_noul() and jev_ask() returning real SQL types, batching 16 rows per request and caching identical queries.
productauthor demo
Support routing inside a shipped Mac app
A Mac app routes setup and troubleshooting questions to the right built-in manual article with Jev when no local model is loaded, showing real docs instead of generated text.
demoauthor demo
Hook scoring against ~100 synthetic personas
Near-real-time scoring of TikTok and Instagram hooks against roughly a hundred synthetic personas with Jev.
demosource-backed
Clarity Judge: seven writing checks
Seven independent writing checks (hedging, filler, passive voice and more), each returning its own verdict, confidence and the driving sentence; runs simulated without a key.
productauthor demo
Yes/No oracle on jev-latest
A free yes / no / maybe oracle that calls jev-latest through the System One API with live search for current facts; no account needed.
benchmarkauthor demo
Jev as a reranker: graded-relevance eval
Evaluates Jev reranking against bge-m3 embedding search over an Agent Skills Hub catalog, with judge-bias and robustness analysis.
integrationauthor demo
jevql: semantic predicates for vanilla Postgres
Adds `jev()` semantic predicates to plain Postgres through a CLI, HTTP and SDKs, with a SQLite cache and an `--explain` cost preview; a playground is hosted.
demoauthor demo
jev-recruiter: LinkedIn recruiting agent
A Jev-driven recruiting agent with a local web UI that shows evidence quotes behind each decision; a short demo video is linked.
demoauthor demo
Telegram channel analyzer with Jev
Load a Telegram JSON export and Jev labels each post's type, quality, sentiment and reaction tone; runs through Vercel AI Gateway or a TypeSafe key, with label export.
demoauthor demo
Jev Paper Judge
Upload a research-paper PDF; text is extracted in the browser, split into roughly 1,000-word passages, and a fixed set of small questions is asked per passage in parallel, then combined into weighted scores.
integrationsource-backed
TrainLCD: Jev re-ranking in a production train app
A pull request on the TrainLCD Functions repository adds Jev-based re-ranking of suggested stations and measured spikes; the author says Jev is also going into part of the app's AI chat.
integrationsource-backed
jev-reranker: relevance filtering and reranking for RAG
A Python package for Jev-powered relevance filtering and reranking, with a Hugging Face blog walkthrough covering the API, filtering and evaluation results.
benchmarksource-backed
llm-rankers: checking Jev's calibration with TREC judgments
The ielab document-ranking toolkit gained a jev module, with code that uses TREC human relevance judgments to test whether Jev's probabilities are actually calibrated.
demosource-backed
transcript-lens: explore YouTube transcripts by meaning
Browse YouTube transcripts by meaning with Jev analysis, subtitle export and a Vercel setup guide; Turkish UI.
demosource-backed
findme: jev + fs
'jev, find me stuff in my system' — a file finder that asks Jev which files match a natural-language request.
reposource-backed
Sniff Test: a prose linter where Jev is the judge
Countable rules plus one judgment model: ten yes/no questions per paragraph flag AI-writing tells. Zero dependencies.
productauthor demo
Jev Detector: an AI-slop detector on Jev
A hosted detector that scans text for AI-written 'slop' using Jev decisions rather than a generative model.
reposource-backed
DocJev: document classification and splitting with Jev
An OSS library from the LlamaIndex founder: give a document plus natural-language category rules and Jev predicts the category (classify) or the boundaries between sub-documents (split). OCR backends: liteparse (fast, free) or LlamaParse for complex layouts.
integrationsource-backed
jev-curate: sift pretraining datasets at 1,500+ rows/sec
A high-throughput sifter for synthetic and pretraining datasets: stream Parquet and JSONL, filter and score every row with Jev.
demoauthor demo
Clipping a 90-minute video by topic in two seconds
Transcript in, topic in, clips out: Jev picks the segments of a 90-minute video for any topic in under two seconds.
demoauthor demo
Predictive spreadsheets: type a column header, Jev fills the meaning
Type 'Urgency' at the top of a column and, as you type, Jev works out you want each row rated from 'no follow-up needed' to 'urgent' — spreadsheets that recalculate meaning, not numbers.
integrationsource-backed
duckdb-jev (prasanthj): native, batched, cached
A native DuckDB extension for Jev classification, scoring and semantic predicates from SQL: vectorized input, batching, bounded concurrency, dedup and cross-query TTL/LRU caching. Distinct from colliber/duckdb-jev.
demosource-backed
jev-shell-history: fish-style zsh suggestions ranked by Jev
Picks the most likely command from the last 100 unique history entries and ghosts it after the cursor, fish-style, using Jev to rank by intent.
demosource-backed
jevyoumean: semantic 'Did you mean?' for any CLI
Wraps commands and uses Jev to match mistyped subcommands by intent, not edit distance: `git record` → `git commit`, `npm add` → `npm install`.
benchmarksource-backed
rerank-bench-jev: Jev versus Qwen3 Reranker
An inspectable comparison of Jev Noul and Qwen3-Reranker-0.6B on retrieval ranking tasks, with the harness and raw model responses published.
integrationsource-backed
Jev decisions in BigQuery through Cloud Run
A Cloud Run remote function lets BigQuery call Jev to classify support tickets and expose the resulting judgments to SQL queries.
integrationsource-backed
ZeroNSFWBot: optional Jev text moderation for Telegram
A Telegram moderation bot that uses Jev for optional text, bio, advertising and language judgments. Image moderation runs through a separate local detector.
integrationsource-backed
gmail-jev: label Gmail threads with Jev
Classifies Gmail threads into workflow labels with Jev and can optionally remove them from the inbox. The tool does not send mail.
integrationsource-backed
jev-linkedin-slop-filter: label LinkedIn posts
A Chrome extension that applies BAIT, CORP and BRAG labels to LinkedIn posts using Jev, with a local server for the API key and heuristics to reduce calls.
integrationsource-backed
JEV DataOps: screen and evaluate training data
A workflow for uploading, screening, training and evaluating datasets, with Jev API calls used for the screening stage.
productsource-backed
ASO Workbench: Jev-assisted keyword analysis
An open-source Mac tool for App Store Optimization with keyword analysis and listing workflows that the author connects to Jev.
integrationsource-backed
CodeNib: Jev reranking for code search
CodeNib uses Jev to rerank code-search results and publishes integration docs plus an evaluation on 100 CodeNib Base issues.
integrationsource-backed
HN Jev Scores: adjustable Hacker News ranking
A Chrome extension scores Hacker News stories on five factors with Jev and reorders the page using adjustable weights.
integrationsource-backed
Spring AI TypeSafe: Java SDK and Jev integrations
A Java System One client plus Spring AI modules for Jev judging, guardrails, retrieval filtering and reranking, and tool selection.
integrationsource-backed
jevgrep: semantic code search for coding agents
A CLI that uses Jev to judge relevance across repository folders, files and declarations, returning file leads and verbatim source excerpts to a coding agent.
demoauthor demo
Y Combinator startup search with Jev
A video demonstration of semantic search over a collection of Y Combinator startups using Jev decisions.
productauthor demo
Treg people search with a Jev screening step
A live people-search workflow in which Jev screens candidate companies against an ideal-customer profile before treg finds and verifies contacts.
reposource-backed
larguesa jev-search: semantic line retrieval
A Python command-line tool uses Jev to find relevant lines in selected local documents and knowledge-base text alongside lexical search.
reposource-backed
JevGrep: semantic source retrieval through CLI and MCP
A TypeScript CLI and local MCP server ask Jev to rank source fragments and return exact excerpts with paths and line numbers to coding agents.
reposource-backed
JevFind: two-stage semantic code finder
A Rust code-search CLI first scores source paths with Jev, then ranks overlapping windows from the selected files and prints matching snippets.
integrationsource-backed
pi-jev-tools: ranking and retrieval tools for Pi
A Pi extension exposes Jev ranking, classification, local snippet retrieval and general typed evaluation while retaining the normal coding model.
reposource-backed
jevgrep jg: Rust natural-language code search
A standalone Rust binary searches a codebase using natural-language questions and returns relevant files and line ranges with scoring details.
benchmarksource-backed
YC × Jev: startup search and a reranking benchmark
An independent reranking benchmark paired with a live natural-language search over Y Combinator companies. The app uses Jev for query routing and reranking after keyword and embedding retrieval.
integrationsource-backed
genigrep: source evidence packs for coding agents
A CLI, MCP server and library combine ripgrep recall with Jev judgments over candidate files and passages. Results contain original source excerpts with paths, line numbers and explicit omitted ranges.
integrationsource-backed
Jev Navigator: code relationships and semantic search
A Python code-navigation library builds a structural index and composes small Jev judgments into best-first source searches. Its commands can trace known workflows or find matching functions while saving source provenance and partial results.
replicasource-backed
OpenDecision: local typed decisions with document evidence
A local semantic engine answers typed questions about application state and documents using an NLI model. It adds evidence retrieval and a Relation primitive alongside a Python API and TypeSafe-compatible HTTP server.
reposource-backed
Oko: local code search and prompt-time retrieval
A local Rust search tool combines keyword discovery with Jev ranking and delivers source excerpts through a CLI or MCP. Its setup command connects Codex, Claude Code and OpenCode and can supply retrieval context when a code question is submitted.
reposource-backed
jevr: BM25 recall and Jev reranking for code and documents
A Rust CLI searches source trees and text documents with local BM25 recall, then uses Jev to filter and order candidate files. Results carry paths, line ranges and relevance scores in a grep-style interface.
reposource-backed
every: ask a yes/no question of each source function
A Python CLI parses source files into functions and asks Jev the same yes/no question about each unit. It ranks the returned probabilities and uses chunks when a language cannot be parsed at function level.
benchmarksource-backed
Jev reranking: saved outputs across retrieval tasks and scoring strategies
A retrieval study compares typed Jev scoring strategies with dedicated rerankers and open-model controls on the same passage candidates. Saved provider responses, query-level evidence, bootstrap intervals and an interactive viewer support inspecting each result.
demosource-backed
Refgarden: spatial reference search with bounded choices
A spatial reference explorer retrieves images and archive clips from source-linked collections. In the local app, Jev selects bounded search phrases and highlights image references from their metadata; collected references can be pinned and exported.
integrationsource-backed
GPT Researcher: Jev context selection
GPT Researcher can use Jev to score scraped passages for usefulness to a research question. Its compressor selects context from the same chunk pool and output budget used by the alternative retrieval pipeline.
integrationsource-backed
MemSearch: Jev memory reranking
MemSearch includes an optional Jev reranker for project-memory passages. Candidate excerpts are scored against the query before the application chooses which memories to return.
integrationsource-backed
ThoughtDAG: Jev conversation recall
ThoughtDAG searches local agent sessions and visual conversation canvases. Its optional Jev layer helps select relevant excerpts and topics before the chosen language model develops an answer.
integrationsource-backed
Hippo Memory: local memory with Jev ranking
A local SQLite memory system exposes retrieval through MCP and can rerank a candidate pool with Jev. Its implementation uses Noul relevance judgments before returning selected memories.
productsource-backed
Needle: semantic search inside webpages
Needle uses Jev to rank passages and select the strongest source sentence for a natural-language query. Its Chrome extension highlights those sentences on the original webpage, and a React interface also accepts pasted text.
integrationsource-backed
GenOffice: Jev file-search ranking
A desktop office suite indexes local document text in SQLite and can use Jev to reorder search results. The optional reranker evaluates candidate files against the search question before showing the ranked list.
integrationsource-backed
XERJ: Jev judgments over search results
XERJ can send retrieved documents to Jev for query-relevance judgments and reorder the result list. Its search implementation keeps the decision step separate from ordinary retrieval scores.
integrationsource-backed
Pi MCP Adapter: Jev semantic tool search
Pi MCP Adapter can rank MCP tools by meaning using a System One evaluator. Project policy specifies which servers may share data for semantic search, alongside the existing word and regex search modes.