All decision model projects

Jev demo that reads live yfinance profiles and headlines into ranked, grounded and routed trade ideas, showing every request.

Rust LLM application framework with an experimental rig-typesafeai crate for typed Choice, Score and Noul Jev queries.

Novelty demo that turns Jev answers to 22 Boolean gate questions into lookup tables for a simulated RISC-V CPU running compiled C.

River Raid-style Python shooter flown by a Jev pilot that picks a lane, whether to fire and a speed in one request per decision.

SO-101 robot-arm workbench where a Jev decision runner picks bounded joint steps from typed candidates under a spend cap.

Early-stage persistent multiplayer RPG where Jev makes every in-world NPC decision, Claude authors the world, and code owns rules.

Gamified Rubik's cube web app where Jev rates your scramble and solves it move by move from the live cube state.

Terminal UI for typed System One decisions that switches live between local laya on MLX and hosted Jev, logging every run.

Public Neon Function gateway that has Jev judge request bodies for prompt injection or unsafe replies before optionally forwarding them.

SAP S/4HANA proof of concept that sends anonymised purchase-order risk indicators to Jev and classifies orders to release, approve or block.

Scam text checker where code extracts link and sender facts, Jev answers eleven narrow questions, and a pure policy scores risk.

Plain-English Playwright end-to-end tests where Jev resolves each step's target element and judges whether verify claims hold.

Chinese real-time captioning app where Jev annotates each spoken sentence for key points, emotion and intent as it streams.

Living-room social-deduction party game where Jev reads game state each round to drive per-player suspicion meters and bluff signals.

Hackathon arena where 200 people attack a support agent and a Jev allow/block/escalate gate on every tool call is hardened each round.

Tech reading feed from Hacker News, Dev.to, Hashnode and Lobsters, ranked by Jev scores against your skill summary.

Experimental voice-driven auto-advance for Slidev that asks Cloudflare's Clef-omni four typed questions when the presenter pauses.

Browser snake arena where eight AI snakes are driven live by Jev, one call per tick with a Choice per snake over legal moves.

macOS window switcher that predicts which app you want on Cmd+` with a Jev Choice over your ten most recent apps.

Resume-fit platform where Jev scores six factual dimensions and returns KILL, FIX or SHIP before Claude adapts a resume.

MCP server and Claude Code plugin that files each captured note with one Jev request deciding kind, project, action and duplicates.

Chinese tool that scans a Bilibili video's comments for rhetorical moves, with eight labels and quoted evidence, optionally via Jev.

Jev-first CLI coding agent that routes a request to a deterministic workflow which asks Jev fixed-choice questions about bounded evidence.

Proof-of-concept Claude Code plugin where Jev checks every pending tool call against the session plan, then allows, asks or blocks.

Toy research agent where Jev makes every keep/skip and delve decision over search results, and one expensive call writes the report.

LangGraph student-support agent with PII masking and hybrid RAG, where Jev verifies drafts before auto-reply or human review.

Python library that turns an open LLM into a Jev-style classifier via constrained single-token choice indexes in one forward pass.

Browser arcade games (2048, runner, chess, Flappy Bird, Sudoku) where small decision models choose each move from text options.

Local PR reviewer: deterministic diff handling plus Jev or Laya judgments of severity, category and true-positive per hunk.

Two-tier macOS decision engine: a MiniLM encoder on the Neural Engine decides, escalating unsure cases to Apple's on-device model.