All decision model projects

Experimental Hono router that matches HTTP requests to plain-language route descriptions using one Jev Noul per route.

Python browser agent where Jev picks each operation and element in about 150 ms, escalating to an LLM only when unsure.

Town simulation in which Jev chooses the next action for each of 100 NPCs while game rules handle everything else.

Natural-language SQLite interface where code proposes options, Jev chooses among them, and a compiler builds deterministic SQL.

Joke npm package that asks Jev whether a number is even, showing the request shape in a few lines.

Local proxy for Claude Code that uses Jev to pick model and effort per message, routing subagents but guarding the cached main chat.

Gives an agent one tool that uses Jev to search a nested capability tree and return only the documented commands a task needs.

Modular Hyperliquid perpetuals trading engine whose DecisionMaker asks Jev for a long, short or flat target per market.

Coding agent where Jev handles context selection, tool routing, plan gating and verification, and the big model sees only key context.

CPU-only local Jev-style decision service plus an oh-my-pi extension that retargets the agent's judge provider to it.

Colab notebook experiment that analyzes a movie review with one Noul, one Choice and one Score question to Jev.

Experimental harness where Jev plays the original Civilization II in a browser, choosing empire, city, research and unit actions.

Chrome extension that converts a page's WebMCP tool schemas into Jev questions to pick a tool and fill its arguments from what you type.

Prototype per-call model router for Codex where Jev picks the GPT model and reasoning effort for each call via a local Responses proxy.

Chat-shaped command bar where Jev picks the tool, arguments, confirmation and reply type, and code builds replies only from tool data.

CLI, MCP server and skill for issue triage where Jev predicts issue kind, affected module and whether information is sufficient.

Six side-by-side demos where Jev makes the decision, Claude or Kimi writes the words, and code owns control flow.

Browser driving game where Florence-2 captions dropped images and Jev decides whether the car stops, slows or continues.

Windows and Chrome GUI delegation for Codex: a local controller runs a task contract, calling Jev only for semantic choices.

Browser 2D driving sim where Jev answers lane, speed, hazard and pedestrian-yield questions every 200 ms, with an LLM comparison mode.

Real-time versus Tetris where Jev and an LLM or open Laya model pick placements on the same seeded pieces and clock.

Talk to your Mac: local whisper.cpp transcribes, one Jev request picks the action and typed arguments, and code executes macOS automation.

Floating macOS bar for voice or text commands where Jev picks the next action from live accessibility controls in a loop.

Crypto terminal that condenses up to 1,000 posts plus market data into a Jev buy, sell, hold or take-profit card; no trading.

Python agent development kit for building System One pipelines with Jev for guardrails, routing and PR triage.

Gives Jev eyes: detects and tracks objects in images, video or RGB-D feeds, then asks a typed Jev question about each object.

Selenium bot that plays 2048.org by fusing expectimax search with a Jev Choice over legal moves on every turn.

Example of Jev as a before-tool-call risk gate in a Google ADK agent, blocking tools when P(risky) passes a threshold.

Local web and voice interface for Codex and Claude sessions in tmux, where Jev interprets each request and Python performs it.

Skill and CLI that compares a shortlist of agents, MCP servers or skills against a task and permission ceiling, abstaining on weak leads.