Jev Codex

A research-stage proposal-review contract in TypeScript: an LLM proposes one action, Jev answers four pinned questions, and code produces evidence the host can consider.

Wrappers for Claude Code and OpenAI Codex that ask Jev to choose a model tier for each fresh user turn while preserving each CLI's native interface, tools, sessions, permissions, and authentication. Ships as the jev-claude and jev-codex commands.

Claude Code, Codex, and pi plugin plus MCP server and npm library that hands steps needing no text output to Jev: one batched call answers typed questions about a state, and an opt-in PreToolUse gate can only deny or ask.

Local Codex Router extension that asks Jev for a model tier and thinking depth on each model call, including continuations after tools, then relays the native Responses request verbatim. Fails open on Jev errors and logs decisions locally.

A security hook for coding agents that asks Jev three typed questions before every tool call and scans tool results for prompt injection, with adapters for Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, pi, OpenCode and ACP.

A local-first MCP server that gives Claude Code, Codex, Cursor, and OpenCode structured quality scores from Jev across correctness, complexity, tests, security, and other dimensions while the agent writes code.

A Codex skill (with a plugin option) that hands clicks, toggles, navigation, and scrolling to Jev over accessibility text while Codex types, interprets visuals, and verifies the outcome.

An experimental local context-pruning proxy for Claude Code and Codex that asks Jev, through the Vercel AI Gateway, which history spans to omit, then forwards a rewritten request with omission markers.

A warden for Claude Code and Codex CLI that keeps an append-only ledger of what an agent did, refuses a done claim when no check passed after the last edit, and uses optional Jev Noul judgments.

A Codex plugin and npm library that wraps native session compaction: Jev scores every tool call and result, and the verbatim history it keeps is re-injected after Codex summarizes. The README does not recommend using it.

An Agent Skill that sends closed coding-agent judgments to TypeSafe Jev and acts on the probabilities, asking for yes/no, choice, and score answers in about 250 ms while the main coding model keeps writing code.

A Stop hook that keeps coding agents from quitting early: rules written in plain language are scored by Jev in about 0.7 seconds, and a violated rule sends the agent back to work instead of letting it stop.

An experimental Codex skill and JavaScript runtime that has Jev pick macOS Accessibility elements and actions from text candidates, while local policy gates hold sensitive operations for human confirmation.

A Codex Computer Use plugin that adds bounded Jev decision loops: Codex scopes the task and defines allowed actions, Jev picks an operation and compatible target in one request, and Computer Use performs the click, fill, scroll, or shortcut.

A structured decision plugin for agent harnesses: Jev recommends among currently available and permitted tools, skills, and agents, and evaluates output quality, returning choices, probabilities, and confidence while the host agent keeps planning and execution.

A local gateway for coding agents that asks Jev which tool to call each turn and steers the LLM when Jev is confident, while every other request goes to your usual provider untouched.

A collection of 26 production-ready agent skills for Claude Code, Cursor, Kiro, Windsurf, and OpenCode; four skills call TypeSafe Jev for calibrated Score and Noul judgments and fall back to heuristics when it is unavailable.

A Jev-guided context compaction library for coding agents: instead of summarizing old context, Jev decides which tool calls and results still matter while user and assistant text is kept verbatim.

An experimental Codex CLI router where a local Responses proxy asks Jev one Choice per model call to select a host-available model and reasoning effort, while application-owned acceptance decides whether the task passed.