Jev in production › Model and agent routing

Grok Bot Jev Router

Python router where Jev classifies each Grok Bot request before research, browser or retry work and returns an action such as reuse cache, stop retry or ask a human. 13.0× shorter wall time in one ranked-research comparison (author).

Open on GitHub ↗

13.0×measured against a baseline, as published by the source
Use
Model and agent routing
Industry
AI infrastructure
Form
Open-source tool
Stage
Beta
Plugs into
Grok Bot
Listed
2026-09-20
Found via
github
Repository
Bodila51/grok-bot-jev
Stars
104
Forks
11
Last push
2026-09-28
Language
Python
License
MIT
Grok Bot Jev Router screenshot
media/jev-grok-bot-dashboard.png in the Bodila51/grok-bot-jev README, MIT; shown from GitHub.

The README opens with

Connect TypeSafe Jev to Grok Bot as a cheap decision layer. Jev classifies the request before expensive research, browser, retry, or subagent work, so Grok Bot can reuse a fresh artifact, stop a failing retry, cap research, or ask for approval.

This package is a small open-source reference implementation. It does not change Grok Bot's foundation model and does not route Cursor models.

- A Python router around the TypeSafe SDK's systemone call. - Explicit actions such as reusecache, stopretry, rundeterministic, chatonly, researchcapped, allowsubagent, and askhuman. - shadow mode for measurement and active mode for a skill that honors the returned action. - A kill switch through enabled: false or a bypass jev marker.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for model and agent routing