All decision model projects

Polars library for parallel LLM inference that also asks Jev per-row Noul, Choice and Score questions through a native Rust layer.

GitHub Action that compiles .jev.yml rules into Jev questions and fails, comments on or passes a PR based on the numbers.

npm library where Jev judges whether an agent's recent steps are stuck on the same assumption; code returns CONTINUE, WARN, REPLAN or HALT.

Parallel web search CLI and MCP server where Jev scores fetched pages and picks which links to follow next.

Go port of PydanticAI's typed agent loop with a TypeSafe Jev model provider alongside the usual LLM providers.

pytest plugin for semantic assertions on LLM output, asking Jev whether plain-English claims hold with a 0.8 probability bar.

macOS menu bar screen-time app that asks Kev or Jev whether each screen breaks your rules and steps in with a pop-up.

Chinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.

TypeScript library for typed semantic decisions via Zod schemas or native batches, defaulting to Jev, with confidence-gated policies.

Claude Code skill that hands bulk 'read a lot to decide a little' judgments over files, logs and tickets to Jev and returns a shortlist.

Chrome extension that drafts WhatsApp and Gmail replies and hides unproductive YouTube videos using a Jev yes/no question per video.

Bot that plays Red Alert 2 web skirmishes, with code handling mechanics and a decision model making stance, threat and timing calls.

Local-first MCP server that returns only Jev-checked passages from big PDFs, Word files and spreadsheets, with exact row calculations.

Claude skill and API that turns a video link into timestamped JSON, then asks Jev typed questions to rank or filter videos against a brief.

Pi-based coding agent where Jev gates every tool call, picks the model tier, checks 'done' claims and trims tool output.

Pre-execution hook for coding agents that lets shell commands run, asks a human, or blocks them, with optional Jev classification.

Computer-use MCP server for macOS and Windows that reads the UI tree and uses Jev to find elements, check screens and wait for states.

Slack-like playground for watching computer-use agents work, with replays, comparable runs and Jev choosing from a menu of visible actions.

Runtime verification framework that drives your real app to check a coding agent's 'done', returning pass, fail or cannot tell.

Ruff-style prose linter whose semantic rules each ask Jev a yes/no question about a paragraph, title or section, with tunable thresholds.

Rust terminal coding agent for local models whose swarm mode can use Jev to referee parallel attempts and pick a typed winner.

Multiplayer 3D science-fantasy version of Houston's River Oaks District with Jev-powered NPC companion, chauffeur and smart drive.

ROS 2 robot diagnostics CLI where an optional agent uses Jev to choose which read-only evidence tool to call next.

Chrome extension that asks Jev whether each video, post or article serves your written goals and blocks or blurs it in code.

Local Rust gateway that exposes Codex, Grok, Kiro or Vercel AI Gateway credentials as OpenAI/Anthropic APIs, including Jev evaluations.

Browser 3D planetary rover sandbox where a TypeSafe controller chooses the next action from complete candidates, versus a baseline.

RubyLLM provider gem for TypeSafe Jev: block-style typed evaluations with noul, choice and score, plus RubyLLM.rerank support.

Code mode for agents: 204 bundled API plugins callable from sandboxed JavaScript, with a TypeSafe plugin exposing Jev as actions.

Claude Code plugin where a local Decider model on your Mac picks the model and effort level for each subagent task.

Code navigation tool where a lexical index proposes candidates and Jev's typed judgments decide which files and lines belong.