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.
Re-rankers, relevance gates and retrieval fusions with per-item costs from each author.
41 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.