Find Your Next AI Superpower

Navigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next.

A CLI and stdio MCP server for typed Jev judgments over text or JSON.

A Python Flappy Bird game where code simulates candidate routes and Jev picks one.

Jev-powered: Semantic pathfinder navigating large codebases without vector indexes using beam search.

A simulated crypto trading loop that sends BTC and ETH market features to Jev and models execution costs and latency.

A toolkit for evaluating Jev probabilities on labeled data, selecting confidence thresholds and checking model drift.

A chat-style Jev demo whose answers are selected from predefined or custom options rather than generated prose.

A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.

An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.

A browser-based 1v1 shooter where Jev reads structured match state and chooses movement, aim, and firing.

A Rust dataset-filtering experiment using Jev scores to keep or reject text records.

Jev-powered: Rust CLI experiments for health-information screening, comment review, tone analysis and business or occupation classification.

An HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.

Exposes a shared structured-decision interface for Jev and other models through ACP, MCP and a CLI.

A word-level generation experiment that asks Jev to select words or verify locally drafted continuations.

Jev-powered: Helps coding Agents locate code, check change intent, triage test failures, and organize review findings.

Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.

Integrates Jev as an asynchronous Elixir/OTP process whose replies are handled with GenServer pattern matching.

Turns Jev judgments into Home Assistant sensors, such as checking whether finished laundry has been left unattended.

A benchmark comparing Jev and GLiNER on text classification, probability calibration and selective automation.

A MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages.

Jev-powered: Adds semantic rules to Zod validation, such as checking whether text matches a description or contains personal information.

Searches the web with Jev choosing sources and time ranges, then ranking returned links.