All decision model projects

Next.js community playground extending the 110-example TypeSafe library with A/B comparisons, routing, extraction, games and simulations.

Community web playground with 110 runnable Jev examples in 22 categories, including A/B comparisons, games and dilemmas.

BYOK practice workbench that emulates Jev's Noul, Score and Choice workflows with ordinary LLMs, or calls native Jev if you have access.

Runs the open LAYA decision model under Bun with native ONNX inference behind a TypeSafe-compatible API, plus an English/Persian playground.

Live Hyperliquid trading desk where Jev chooses long or short and open, close or hold each tick for five coins, with dry-run by default.

Draw on a tldraw canvas by voice while pointing a webcam-tracked finger; Jev decides command, action, shape, colour, target and place.

Pokémon Red on PyBoy where code owns route and arithmetic, Jev picks only at branches, and battle faint predictions are Brier-scored.

Local Snake battle where four NanoJev AI snakes pick moves from a candidate distribution while you play the fifth.

Visualizer that sends every passage of a novel to Jev for nine emotion scores plus intensity and draws the book as an aurora poster.

Small demo for small-business checkout fraud disposition using Jev; the repository README is a one-line description.

Workbench that turns OpenAI chat requests into Jev state and questions, compares both outputs, and publishes question sets as proxy routes.

Pygame chess where python-chess owns the rules and Jev picks one labelled legal move per turn, with Human or Jev on either side.

ComfyUI custom nodes that use Jev to select candidates, judge conditions, score text, extract numbers and choose local Skills.

Reliability testing for typed decision models: contracts, calibration metrics, metamorphic fuzzing and CI pass/warn/fail gates.

Browser agent that acts on one look at the page with one open-model call per action; Jev is an optional chooser backend.

Symfony demo that triages French public-service requests with one Jev call each: intent choice, urgency score and bug noul.

Open protocol for decision-based agents: apps expose evidence and typed decisions, Jev assesses, and app code guards commits.

Playful web app where twelve absurd characters vote on your idea via one Jev request with 36 independent questions.

Fixed-wing landing simulator and benchmark where Jev maps four Choice decisions to aircraft controls against humans, baselines and LLMs.

Cloudflare Flue agent example that adds a validated route_with_jev tool for typed support routing through AI Gateway.

Learning demo that sends the same input to GPT for text and to Jev for three Noul probabilities, side by side.

Comment-moderation demo: one Jev call screens seven hazard Nouls and a severity Score, with the verdict computed by policy thresholds.

Decision board where one Jev request picks which of eleven livestream ideas becomes tonight's MVP, with code gating and weighting.

Minimal web demo: paste an agent step trace and Jev judges whether to continue, retry, escalate or stop.

Small demo that scores resumes for first-pass fit and interview recommendation with TypeSafe Jev.

Next.js demo where Jev picks real shadcn/ui components and settings from a fixed catalog to render a described UI.

Browser teleprompter that checks off talking points as you cover them, scoring each with a parallel Jev Score question.

Research notes on Jev plus a live Cloudflare Worker playground that triages support messages by department, urgency and frustration.

Ten runnable JavaScript lessons where Jev judges agent situations like memory conflicts and handoffs while code enforces explicit policy.

Async LangGraph example where a Jev Choice labels each email as invoice or general and routes it to a handler.