All decision model projects

F1 racing game where Jev picks racing line and pedals several times a second and learns corner limits between laps.

Neo4j demos using Jev as a calibrated judge in GraphRAG pipelines, starting with entity resolution and a review queue.

Toy chat that makes Jev talk by repeatedly choosing its next word from a tiny caveman vocabulary.

Experimental browser-only MCP server where Jev picks a code-owned action ID and a human approves before execution.

Blender extension where Jev ranks about 2,500 operators against a plain-language request via a two-stage Choice search.

Turns an inbox into a short action queue: seven Jev questions per thread decide what needs you, urgency and next step.

Python example classifying customer support messages into 12 intents with Jev, flagging clarification below 0.8 confidence.

Smart-meter fleet dashboard where code pre-filters telemetry and Jev classifies anomalies for remediation across millions of endpoints.

Read-only GitHub dashboard where Jev classifies candidate issue pairs as duplicate, related, distinct or underdocumented, with evidence.

'Vitest for LLM outputs': CLI running YAML/JSON eval suites on Jev for RAG faithfulness, hallucination and agent safety in CI.

Developer preview adding Jev candidate reranking to the Rime (Squirrel) Chinese input method on macOS with a Ctrl tap.

Turkish natural-language outerwear search where Jev decides in two steps, code filters and ranks, and a panel shows each step.

Spanish-language progressive learning lab for Jev built with spec-driven development, starting with a hexagonal skeleton.

Deliberately silly npm package that left-pads a string by asking Jev to choose how many spaces to add.

Chrome extension stamping LinkedIn posts BAIT, CORP or BRAG with Jev confidence, after free local keyword rules.

Rebuilds a site's internal link map with Jev judging thousands of link candidates, raced against Claude Opus 5 on the same queue.

Python CLI that shows which OpenAI model Jev would route a query to, independently reviewed by a local Ollama model.

Python library that imitates Jev-style typed decisions (choice, score, yes/no) on local LLMs via Ollama, vLLM or llama.cpp.

Read-only Chrome extension that badges each Gmail message with Jev's category, priority, spam % and reply %.

Email triage proof of concept: one Jev call with 11 narrow questions per message, combined in Python into kind and topic labels.

Paper-trading demo that turns live BTC, ETH and SOL market state into Jev BUY / SELL / HOLD choices with deterministic risk rules.

Proof-of-concept MCP tool dispatcher that routes a natural-language command and extracts arguments using only Jev Choice and Noul.

Browser Minesweeper demo where Jev answers 'is this cell a mine?' for every frontier cell in one request, with an exact solver as fallback.

MLX library that turns an existing local model into a decision engine by reading candidate logits, with no fine-tuning, on Apple Silicon.

Android agent where one Jev request per step picks an operation and target from the accessibility tree, with a vision fallback.

Web chat where one Jev Choice picks nano, fast, balanced or frontier model tier per message via the Vercel AI Gateway.

Python router where Jev classifies prompt difficulty and stakes, then confidence-gated rules choose an OpenAI model tier.

Claude Code hook and skill (German docs) where Jev picks the cheapest sufficient Claude tier and whether to delegate to a subagent.

OpenAI-compatible streaming proxy that holds tokens in a buffer and releases them only after a Jev check passes, cutting leaks pre-screen.

Minimal FastAPI and React workbench where Jev picks metadata values such as genre for local audio files and writes them back.