All decision model projects

Effortlane: local router for native Codex on macOS that uses Jev to recommend model and reasoning effort per turn, with a Shadow mode first.

Browser arena shooter whose enemy tactics were first chosen by Jev Choice questions, later replaced by a local utility scorer.

Taboo-style browser game where Jev guesses which of 135 UI components you are describing and buzzes at 0.85 confidence.

Go macOS controller where Jev picks the next accessibility action, the target element and whether the goal is done.

Korean RL tycoon game training a company decision model that answers situations with choice, probabilities and confidence.

Local chat analyser that labels each WeChat message's emotion and intent with Jev and grades how your replies landed.

3D Rubik's Cube app where local planners simulate candidate move sequences and Jev picks one at each of seven solving stages.

Three.js cyberpunk arena shooter where Jev drives enemy tactics, an encounter director and an autopilot bot via Choice, Score and Noul.

Read-aloud English tutor: streaming ASR transcribes, then Jev judges word by word whether each word was read correctly.

Adapter that turns existing LLMs into Jev-style decision functions with option scores, optional calibration and review thresholds.

Pulumi example where Jev picks the best cloud region and modules per user location while code does pricing math and provisioning.

Self-hosted memory MCP server on Cloudflare Workers where a Jev layer judges memory type, salience and durability and re-ranks recall.

Experimental Dice Chess bot planner where Jev chooses among all legal continuations by walking the legal-turn tree.

Next.js app that runs one Jev call on a public GitHub PR to score risk, review depth, blockers and a verdict.

CLI that classifies an artist's discography by theme, mood and lyrical complexity with Jev and shows a terminal dashboard.

ViZDoom agent where Jev picks macro goal, target, movement, rotation, jump and fire at about 10 Hz from a YAML situation report.

Doom runs as a spacecraft payload over real flight software; Jev pilots from the ground every half second while Claude reviews.

Experimental editor that scores X drafts live on six viral dimensions with one Jev call, with a heuristic fallback.

Discontinued DeepSeek Harness decision layer whose policies let Jev only narrow permissions and fail closed; successor is jevcore.

DeepSeek Harness bundle registering a jev_ask tool for typed noul, choice and score questions to Jev.

DeepSeek Harness jev_decide tool that brings the Jev decision paradigm to any OpenAI-compatible LLM, or to real Jev with a key.

DeepSeek Harness plugin for budgeted, read-only GPT 'teacher' consults; Jev may only suggest when a consult is worthwhile.

Six-file DSPy coding agent where Jev answers closed questions (safety, tool fit, history, delegation) and Python owns policy.

OpenAI-compatible local server pairing a small llama.cpp model for generation with Jev for the closed decisions.

macOS command palette that asks Jev one yes/no per menu item and presses the best match for your plain-language request.

Small bounded loop joining ego-lite snapshots with Jev choices over a fixed action space mapped back to observed refs.

Decision sidecar and Copilot CLI pre-turn hook that mimics Jev choice, noul and score using Azure Foundry Cohere Rerank.

Emoji autocomplete that asks Jev eight parallel questions per typing pause: emoji choice, emotion, mood, urgency, sarcasm and more.

AI companion emotion system that reads emotions from the companion's own written thoughts with Jev probabilities via OpenRouter.

Pairs Jev with the get-fable lifecycle harness to give coding agents fast tool and skill routing and verbatim-preserving compaction.