Codex + decision models

AI life-and-civilization simulation where Jev makes every person's next action as an auditable Choice and LLMs only plan.

Desktop computer-use agent for macOS and Windows where Jev chooses each concrete native action, with optional GPT-6 Astra planning.

Claude Code skill that splits work into PBIs for Codex, Antigravity or Claude sub-agents, using Jev for model choice and triage.

Router that asks Jev or another classifier how much reasoning effort each coding-agent step needs, without breaking the prompt cache.

Linear-backed work ledger for coding agents where a Jev-compatible model verifies done reports, blockers and plan changes against the task.

Local context-pruning proxy for Claude Code and Codex where Jev decides which history spans can be safely omitted.

Deterministic evidence selector for noisy Codex investigations; its earlier Jev subagent router is kept for the record, not recommended.

Factorio agent on FLE where Jev picks goals, next actions and stuck detection while code owns rules and actuation.

Independent 52-page Chinese report on Jev that checks vendor claims and reproduces 50 Chinese tests, with traceable data.

Archived Go harness finding Jev tool steering does not reliably cut agent tokens in Claude Code or Codex; context trimming helped.

Learning project benchmarking zero-shot Jev and GPT models against scikit-learn classifiers and ModernBERT on five datasets.

Chinese Slay the Spire 2 agent research: code handles rules, cheap Jev makes most choices, a stronger model takes key moments.

Recorded benchmark of Jev versus two frontier LLMs on 100 synthetic security-triage cases, with a static dashboard.

Official TypeSafe agent skill and Claude Code plugin that teaches coding agents to design System One workflows with typed judgments.

Coverage, security and quality CLI where Jev answers yes/no property questions per file so agents know what to fix first.

Unofficial skill teaching coding agents to design for Jev, with code sketches per pattern, links to 150+ projects and an eval harness.

Zilliz's cross-agent Markdown memory with an optional Jev reranker that asks yes/no relevance questions about retrieved chunks.

Swift library and CLI for Jev with enum-typed Choice, Noul and Score questions, plus an agent skill for coding agents.

Code search CLI and agent skill (jg) where Jev judges relevance across folders, files and declarations to return excerpts.

MCP server exposing a judge tool for typed noul, choice and score questions over JSON state, backed by Jev.

Orchvia: local engine with TS and Python SDKs that runs Claude Code and Codex agents as a team, routing tasks by code and typed decisions.

Stop hook for Claude Code and Codex that refuses 'done' until a check passes after the last edit; Jev advises but never causes a block.

Standard-library MCP server giving Codex advisory Jev tools for role and resource selection, with local validation and 85 offline tests.

Native Bend executable that owns agent-launched processes and logs, and asks Jev a typed question only when told to.

npm CLI that screens large agent tool outputs with Jev, returning compact typed decisions and IDs while originals stay recoverable.

Python MCP server wrapping Jev as classify, score, check, match and screen tools with confidence on every answer.

Local MCP server putting Jev in the coding loop: route next steps, pick prepared tool calls, review patches and verify claims.

Claude Code, Codex and pi plugin that hands non-writing agent steps to Jev and escalates writing or unsure steps to the LLM.

MCP server, CLI and Claude Code skill with Choice, Score and Noul primitives and a confidence gatekeeper, hosted or offline.

Zero-dependency Node library with MCP and ACP adapters adding Jev decisions and gated computer use beside any LLM agent.