All decision model projects

Scaffold of n8n workflow patterns using Jev for PII screening, agent guardrails as hooks, and workflow evals with Jev as judge.

Jev plays NetHack 5.0: code lists the legal moves each turn, Jev picks one with a choice question, and a motor types the keys.

Claude Code plugin that routes every subagent spawn through Jev to pick its model, effort and tool profile.

Python library to batch, gate, trace and calibrate thousands of typed Jev decisions, maximising questions per call.

Node experiment where Jev picks the next step around a coding agent, with approved actions and Codex or Claude Code delegation.

Local browser app that turns Jev's per-pixel colour probability distributions into textured paintings.

Classifies 1,000 arXiv AI papers into 24 topics with one Jev Choice each and checks agreement against an LLM judge.

Android control prototype with three agents: vision model, text-only supervisor, and Jev choosing actions and checking completion.

Local-first personal-data inventory tool with optional Jev classification per column, not per row, and dry-run payload review.

UiPath prior-authorisation triage agent with a Jev guardrail that measures and records PII crossing the model boundary without masking.

Three.js driving simulator with a fast reflex layer, a TTC safety brake and an optional Jev API strategy layer.

Agent skill and CLI that chains Jev question design: find decision calls, check fit, draft, lint, calibrate thresholds and plan a cascade.

Jev plays a browser table-tennis game in real time, choosing serve direction, contact angle and pace from structured telemetry.

Web app that sorts large playlists by each song's main singing language using Jev, in batches of 100 with four in parallel.

Pokémon Red agent on PyBoy where Jev reads a text snapshot of game state, answers parallel yes/no button questions and picks goals.

Agent skill that predicts which closed-set outcome another skill would reach, by asking Jev instead of running that skill.

Support-ticket triage pipeline where Jev scores every ticket and Python decides whether a general LLM should write a reply.

Jev-protocol-compatible random baseline server in Rust: answers noul, choice and score with fast pseudo-random numbers, as a mock or floor.

Electron app running paper-trading agents on live stock or crypto prices, with Jev calling up, down or flat every second.

Local recruiting workspace where Jev browses LinkedIn, screens titles and checks profile excerpts against a hiring brief.

Multi-drone simulation where Jev makes fast reflex decisions per drone and an optional slower LLM may advise but never takes control.

Codex skill and Python CLI for local video remixes with shot and beat detection, Jev clip judgments and an originality report.

Guide and small prototype for using Jev with Herdr to route tasks to coding agents like Claude, Codex and Hermes under code-owned policy.

CV review app where Jev makes traceable document-level judgments on clarity, contribution and results, optionally against a job posting.

Resume knockout tool: deterministic date math and hard gates first, then a Jev decision gate, producing disqualify or advance verdicts.

Staged code-review workflow for JS/TS where Jev screens risk, picks evidence, classifies mechanism, scores severity and routes reviewers.

Autonomous PR review bot with typed Jev questions, deterministic approval gates and escalation of uncertain reviews to trusted owners.

Pipeline that ingests Google Maps restaurant reviews and classifies sentiment, five rating pillars and flags with Jev or an LLM.

MIDI motif ripper: code mines repeating interval patterns and one batched Jev call grades each candidate's musical significance.

CLI that asks Jev which AI app should handle a task (Claude, ChatGPT, Cursor or Antigravity), then opens it and pastes the prompt.