Repo · Coding & code review

jev-use

Hand the steps of a Claude Code, Codex, or pi loop that produce no text — did the build pass, which element to click, is this command safe to run —…

Open github.com ↗

How builders describe it

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

Hand the steps of a Claude Code, Codex, or pi loop that produce no text — did the build pass, which element to click, is this command safe to run — to Jev, and take back the ones it should not decide.

Hi everyone. Recently, Jev has been performing exceptionally well, though there is still some gap in its integration with LLMs. To address this, I created the jev-use project, which allows tasks that don't require text output to be handed directly to Jev. This accelerates overall task execution and…

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 227 coding & code review projects →

Related projects