Jev in production › Model and agent routing
Plugin and MCP server for Claude Code, Codex and pi that routes agent steps needing no text output to Jev (check, pick, rate) and gates shell commands via a PreToolUse hook. Dangerous commands denied in ~230 ms (author).

The best way for Claude Code, Codex, and pi to work with Jev: hand the tasks that need no text output to Jev — faster steps, fewer tokens, tasks done sooner and better.
It makes the LLM and Jev true collaborators: when content needs to be written, the LLM takes over; when a step just needs a fast decision, Jev executes it.
Directions task: Jev clicks, the LLM types — 10 decisions (p50 274 ms) · 4 writes; Jev rejects a wrong route, the LLM rewrites Context compaction — 200 messages judged in 7 calls, one LLM paragraph replaces the dropped pile; recall 3/3
For the project's own README, linking back here: