All decision model projects

Grep by meaning: a zero-dependency Node CLI where Jev scores each line against a described meaning, combinable with AND/OR/NOT.

Go CLI and single-binary MCP server giving Claude Code, Codex, Hermes and pi an evaluate tool backed by Jev, d1, CLM or Laya.

Provider-neutral TypeScript runtime: write choice, noul and score once and run them on Jev, Reflex or any System One endpoint.

Rust port of TypeSafe's system-one-adapter that answers System One questions with OpenAI or Anthropic LLMs for comparison with Jev.

Browser chess lab where Jev, LLMs and people play, each Jev turn being one Choice over the legal moves, with Stockfish analysis.

Prebuilt browser, computer-use, robotics and game agents whose actions come from Jev, Laya or Cua-S1, with a scaffold for new agents.

Unofficial Go client for TypeSafe System One with generics that bind each choice, score and noul answer to a declared Go type.

Chrome extension that sorts every tab into named groups with one parallel Jev Choice per tab, or via an LLM that invents group names.

Local open-source work assistant that turns mail and tickets into agent tasks, with an optional Jev condition-check module.

CLI design and copy linter: mechanical checks block commits, while fuzzy taste checks go to Jev for probability-scored review notes.

Thirty worked Jev uses in ten levels, from a smart if statement to a pi coding agent that writes its own Jev questions.

MCP server and agent skill for designing Jev judgments: question linting, batch evaluation, threshold calibration and reranking.

Tern plugin that beeps when a coding agent finishes or needs you; Jev picks mood, voice, pitch, pace and energy for the sound.

Interactive art piece where Jev reads a post as 100 fictional observers, picking an intuition and scoring four feelings for each.

Command-line tool and SDK that answers typed questions about text with true/false, a label or a number, for scripts and evals.

Policy-driven router that sends each LLM request to the cheapest capable model tier, escalating when Jev finds a reason.

Monitoring proxy and client that records Jev answer probabilities and alerts on version changes, drift, edge crowding or accuracy drops.

CLI that routes a task to one specialist Agent Skill from a Tink library using Jev, then verifies and prints it.

Rust harness for desktop and browser automation where Jev answers small closed questions about the screen to pick each action.

macOS app showing each Claude Code or Codex session as a bird; Jev optionally flags abusive messages and plain-text questions.

JS and Python library that selects and prunes agent tools and MCP schemas, using offline vector search or Jev with calibrated probabilities.

Tool-call firewall for Claude Code hooks and MCP servers: Jev answers seven risk questions and code maps them to allow, ask or deny.

Local-first desktop and Android attention workbench that extracts deadlines from WeChat and campus notices; Jev optional.

Self-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.

Zero-dependency HTTP traffic and bot defense gate that can escalate requests to Jev for five typed risk questions.

Unix filter for security alert triage: JSONL alerts in, Jev answers five typed questions, code routes each alert.

Prompt router for Claude Code, Codex and Antigravity that picks model, effort, skill and language per request via Jev.

Rails gem for intent search: Jev answers declared questions when records are saved, and searches become weighted SQL over those answers.

Browser automation where Jev picks every step from a sightmap's named actions and reports whether the goal is met.

Chrome extension that scores loaded X posts against your reading goal with Jev and ranks top matches pairwise.