All decision model projects

macOS voice and typed computer-use app where Jev picks the next on-screen action from the Accessibility tree, with no screenshots.

Pre-alpha Rust and Tauri voice control layer for macOS that reads the accessibility tree; Jev is a fallback rather than the router.

Node app that controls Chromium by voice, asking Jev a dozen typed questions per partial transcript to act before you finish.

Chinese Chrome extension for web automation where a Jev-style decision model picks elements and beam search finds routes.

Windows UI Automation backend for arc-cua that lets a planner hand off desktop subtasks to a Jev-driven click-and-type loop.

Electron app for controlling Windows 10/11 by Turkish or English speech, using OpenAI Realtime, Jev decisions, UI Automation and Playwright.

Chrome extension that scores X timeline posts on five dimensions with Jev and dims or collapses them according to your sliders.

Play Chinese Chess against Jev, which scores every legal move 0-4 in one parallel call and plays the highest, with no search.

Chrome extension that asks Jev to score YouTube videos as likely time-wasters and covers them with a dismissible shield.

Jev plays Zork I through Jericho, choosing one command per turn from valid actions, with code-owned memory and anti-loop rules.

macOS WeChat helper where an LLM drafts replies and Jev classifies intent, rates risk and ranks the candidates; you press send.

Amp plugin that asks Jev to compare supplied alternatives against supplied evidence and priorities, as advisory input only.

Jev plays Vampire Survivors via a BepInEx plugin and Python brain, choosing character, stage, level-ups and movement.

Browser lab where Jev plays many 2048 games in parallel with one Choice per move and an editor for the state format it receives.

Agent where Jev plays a real online 2048 website through Playwright with one API call per move and no text-generating model.

Tool where Jev clicks through your web app from plain-language steps, stops below 80% confidence, and a vision model checks pages.

Spectator demo where two independent Jev agents play Snake side by side by clicking indexed direction buttons in separate iframe browsers.

Python batching proxy that asks the same Jev questions about many states and streams answers back as Apache Arrow tables.

Companion that answers only with facial expressions: Jev picks one of 16 moods for each message and a blob avatar morphs its face.

3D football match where each of 22 players is an independent Jev Choice over locally computed options, batched into one request per tick.

Python Flappy Bird where the game simulates candidate flight paths through each gap and Jev picks one per pipe.

Windows tray proof of concept that re-picks Bopomofo homophone candidates for a whole sentence with Jev before you press Enter.

Imports agent traces from LangSmith, Langfuse or OpenTelemetry and tests whether a smaller decision model can make routine choices.

Stdlib Python primitive for asking N items K typed questions in bounded, fail-open Jev requests, refusing out-of-set answers.

Creative npm package that makes UUID v4-shaped strings from Jev's probabilities on prompt variations; not cryptographically random.

Strict-allowlist shell harness where Jev walks a TOML decision tree to pick a bash command, flags and paths, confirming writes.

Tool that lets code and agents ask Jev typed questions via reusable jevels, mapping answers to act, mark or fall_back.

Jev walks a real Pokemon FireRed ROM: code reads RAM and lists reachable destinations, Jev picks where to go and how to fight.

Chrome extension that autofills forms from plain-text notes by having Jev match each field to the best line; skips passwords.

ChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.