Jev Search

A browser extension plus Cloudflare Worker that scores search results before you click: Jev answers six questions per page (relevance, depth, SEO filler, sales page, page type, key passage) and code combines them into a 0-100 badge that re-ranks Google, Bing, DuckDuckGo and 104.com.tw.

An Elasticsearch-compatible autoindex search layer that optionally sends top hits to TypeSafe Jev and reorders results by relevance scores.

An independent evaluation of Jev in three retrieval stacks, with recalculated recall, latency, and cost against DeepSeek, GPT-4o-mini, and GPT-5-mini baselines.

Describe the startup you are looking for and Jev ranks the pile, asking once per startup whether it is a fit.

An MCP server for Antigravity IDE, Cursor, and Claude Code that uses Jev (jev-latest) to locate code semantically and audit git diffs, replacing broad grep sweeps of entire files.

Neovim plugin that splits the buffer into functions with Treesitter, asks Jev one plain-language question per function, and fills quickfix with the hits ranked by probability. It judges the unsaved buffer rather than the file on disk.

Reranking benchmark that gave Jev, Cohere Rerank 4 Pro, ZeroEntropy zerank-2, and DeepSeek the same thirty BM25 candidates across eight English datasets, publishing saved responses, scoring code, and paired-bootstrap intervals. Jev's rubric scored 0.692 nDCG@10 against Cohere Pro's 0.691.

A Bun CLI that searches a codebase with an ensemble of walkers: Jev scores file and folder names, more likely paths get more walkers, and the table shows where the walkers ended.

A Rust CLI and MCP server that reranks live DuckDuckGo SERPs with Jev and audits SEO/GEO readiness (schema, robots.txt, sitemaps, llms.txt) with a fifty-rule engine, no paid SEO subscriptions, and a local SQLite history.

A semantic grep CLI that chunks files or staged diffs into 5-60 line pieces, packs 16 chunks and 16 Jev Noul questions into one request, and prints file:line hits above a probability threshold with grep-style exit codes.

A CLI that reranks, filters, or extractively compresses JSON retrieval results by asking Jev separate Noul questions, then lets Rust apply the order and thresholds, reading stdin and writing stdout.

A demo application that navigates a Neo4j graph one hop at a time: Jev gets the outgoing relationships as a Choice plus a goal Noul in one system_one call, and beam search follows the probabilities.

A graded relevance evaluation of Jev as a reranker: 9,831 labelled pairs from 164 queries over a 33,047-item skills catalog, comparing Jev score reranks with BM25, bge-m3, and rank fusion.

A semantic code search CLI that asks one yes/no Jev question per function and ranks the returned probabilities, screening a whole codebase for a pattern in seconds for cents.

A Rust CLI and stdio MCP server that grounds repository and crate discovery in live GitHub and crates.io metadata, then lets Jev score candidates so only verified, installable packages are returned.

A grep-style CLI where the pattern is a plain-English description: each line becomes one Jev Noul question, judged concurrently with matches printed in input order, working on tail -f as well as files.

A sort CLI where the key is a plain-English description: Jev compares texts in pairs, jsort fits a Bradley-Terry scale to the answers, and prints each score with a standard error.

A Python library that reranks search results and filters retrieved documents with Jev, scoring each candidate's usefulness as evidence and dropping those below a configurable threshold before RAG context is assembled.

A streaming grep-by-meaning CLI that judges each line with one Jev yes/no question and prints the lines above a threshold, built to sit behind tail -f, kubectl logs -f, or journalctl -f.

A CLI and Python library that selects source-linked evidence within a token budget using Jev Noul relevance judgments plus local diversity-aware selection, with no labels, vector database, or generative model required.

A terminal Wikipedia link-race tool: Chromium fetches article pages, Jev ranks their outgoing links by expected remaining hops, and Python runs a beam search without a search API or a controller model.

A local SQLite memory layer for CLI agents with an opt-in Jev reranker that batches Noul judgments over the top 40 recalled memories and falls back to a local cross-encoder on errors.

A cross-platform memory layer for AI coding agents: conversations from Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode become Markdown memories indexed in Milvus, with optional Jev reranking through the TypeSafe API.

A local browser agent that reads social media by driving your signed-in Chrome across Xiaohongshu, TikTok/Douyin, Instagram, and LinkedIn; a companion Jev Social demo lets Jev choose bounded socai CLI operations and produce a source-linked report.

A curated, awesome-lint-clean list of projects built on TypeSafe's Jev, the first System One model, with a searchable site whose search is reranked by Jev and a "know before you build" section on limits.

A local 3D reference gallery where Jev chooses search phrases and highlights matching Met, NASA, Cosmos, and Prelinger Archive items from their text metadata.

A zero-dependency Node library and CLI that adds Jev natural-language predicates and decision tables to SQLite, with batching, caching, review queues, and saved decisions queryable as ordinary SQL tables.

A free no-signup demo that turns any question into Yes, No, or Maybe by calling jev-latest through TypeSafe's System One API, with live web search for questions that depend on current facts.

A Neo4j integration where Jev picks the next relationship to follow at each node, turning graph navigation into a sequence of typed choices.

A measured search reranking run over 33,047 catalog entries, 164 real queries, and 9,831 labelled pairs, reporting how Jev compares with BM25 and bge-m3.

Semantic search over GitHub's Terms of Service: one request ranks all 218 lines with a Choice while a Noul checks whether the document contains an answer at all, including when it should say no.

Score retrieved passages with four Noul questions each, then route in code: prompt injections dropped, false premises kept as conflicts, and evidence assembled separately for the generator.

A web-search app where Jev picks sources, time ranges, and query terms, then ranks results from a dozen engines through Search1API, returning links and relevance scores instead of generated answers.

Grep by meaning instead of regex: Jev scores every line, meanings combine with AND, OR, and NOT, and one query matches across Japanese, French, German, Spanish, and more.

One question per query-candidate pair raises top-1 accuracy from 5% to 18% and top-10 accuracy from 38% to 62% on 40 CLERC legal queries.