All decision model projects

Local-first, outcome-aware model router for coding harnesses that picks a capability tier per task with Jev and learns from history.

Chrome extension that labels the tone of Bluesky posts and drafts with Jev and can blur or collapse matching posts.

Python sandbox turning Jev issue-category and reproduction judgments into testable routing proposals, with offline replay.

Stock terminal that gathers live evidence via Valyu and asks Jev for the probability a stock trades higher in 30 days.

Python dialect that adds a '~' operator and jev/case blocks so a branch can ask Jev a yes/no, scale or choice question.

Experiment running a trained jevlike option scorer as ESP-IDF firmware on an ESP32 microcontroller.

OpenTelemetry Collector processor that asks Jev how useful each metric is from its metadata and applies keep/drop policy.

Browser agent with no LLM: code enumerates options from the page and goal, and Jev only picks actions, values and when to stop.

Three.js driving simulator where Jev picks among locally sampled steering-and-speed paths while code handles geometry and safety.

GitHub App that asks Jev to classify each pull request as LOW, NORMAL or SPECIALIST risk and maps that to approve or request review.

YouTube comment analyser: an LLM writes a per-video rubric once, then Jev scores every comment and code computes consensus.

Gallery of small Python demos where Jev answers typed questions on realistic state and explicit policy decides the action or fallback.

EVM token screener that returns ape, watch or avoid with probabilities and risk scores, via library, CLI exit codes or MCP.

Proof-of-concept scanner that asks Jev hundreds of bug questions per Solidity file and writes a heat map of likely vulnerabilities.

Early language design where typed Jev judgments are a runtime operator, with an engine that batches judgments over shared state.

Web app that has Jev judge a note.com article's writing quality on eight Score axes plus an overall AI-slop choice and score.

Text-to-SQL experiment where Jev answers typed questions about the request and code assembles the query, so the model never writes SQL.

Visual workbench (in Portuguese) for wiring Jev decision funnels as node graphs and watching them play a game in real time.

TypeScript library and CLI for exploratory browser testing where Jev chooses actions and judges results and Playwright executes them.

.NET 10 and React 19 ticket triage where Jev answers five typed questions in one call and .NET business rules make the final routing.

OpenTelemetry trace processor that asks Jev whether an operation is diagnostic, business-critical and worth keeping, and annotates spans.

Experimental Polymarket bot: a web-search model writes an evidence brief, Jev prices P(YES), and code trades only on a configured edge.

CLI wrapper that, on an unknown subcommand, asks Jev which documented subcommand you meant by intent rather than spelling.

General-purpose agent loop where Jev chooses each tool call and its arguments and Jot executes it until a reply is ready.

Learning lab for DeepEval with Jev as the judge: replayed evaluations, adjustable decision rules, release gates and drift alerts.

Russian-language Letta agent skill that uses Jev as a fast external judge, with rules for treating mid-range probabilities as 'unsure'.

Experimental trading bot for Kraken, Alpaca paper and OKX with Jev-assisted strategies and code-enforced sizing and risk limits.

Educational code where a local LLM voices a game NPC and Jev classifies player messages and checks every line for spoilers.

Enhancement pack for MiniMax Code CLI on local DGX Spark hardware, including a Jev-style local decision browser agent and context patches.

Mac desktop pet agent that does tasks across files, apps and websites, using Jev alone for file chores and an LLM for open-ended work.