Jev Search
Jev chooses sources and query settings, then re-ranks results returned by search engines. It does not generate an answer.
SELECTED DEMO PREVIEWS
15 selected interfaces and recorded runs. Explore a preview, read the evidence, then open the author's demo.
These are attributed stills, captured screenshots and recorded replays. Each card keeps its evidence label. Media policy → · Selection
Availability checks: daily · Last pass 541/541 destinations · .
No demo previews match this check status.
Jev chooses sources and query settings, then re-ranks results returned by search engines. It does not generate an answer.
A bot that asks Jev for a buy/sell decision on every Monad block from a price feed and executes on Kuru's MON/USDC book, with a live status page.
A Taboo-style game where a player describes a UI component without its forbidden words and Jev ranks the component library. A second mode finds a component from the job the player needs it to perform.
A configurable LIBERO robot-control experiment that combines Jev decisions with reversible physics previews. An interactive replay follows intent, motion family and control choices alongside saved trajectories.
An independent Jev-style project that freezes a language-model backbone and trains a small decision head over cached candidate features. It publishes typed probability outputs, datasets and browser presentations of its benchmark and game policies.
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.
A dynamically branching form where Jev chooses the next question, built on Vercel's json-render for generative form UI and xstate for state — replacing hand-written if/then logic.
An independent Jev-like model fine-tuned from Qwen3.5-0.8B-Base to choose legal actions from raw game frames. The project publishes model weights, training records and a gallery of ten browser games.
A text game where you talk your way past a border inspector whose actions are chosen by Jev from your typed replies; dialogue and consequences are authored game code, Jev only decides.
A Clash Royale experiment on an Android device that converts screen video into structured game state. Jev selects a strategy, card and placement, while the replay viewer exposes the questions and option probabilities.
A one-page web app where Jev plays chess against any OpenRouter LLM, Stockfish, or a human, showing live moves, Jev's move probabilities, saved games and win rates.
A layer that decides when an agent's stored memory should be invalidated, using Jev checks; a playground is hosted.
An end-to-end research toolkit builds decision records, trains and calibrates candidate scorers, and serves a Jev-compatible API. Its released Qwen3.5-0.8B model ranks supplied web actions, while the public demo presents recorded Mind2Web decisions.
A task-specific pipeline generates or labels data with an LLM teacher, trains a LoRA and decision head, then evaluates and serves Choice, Score and Noul probabilities. A public support-triage replay shows saved model outputs and review routing.
An independent family of LoRA adapters and scalar decision heads returns Choice, Noul and Score outputs over pinned Qwen backbones. The project publishes training data, evaluation records, a CPU classification workbench and interactive saved-decision replays.