Skip to content

Jev directory

Effortlane

Effortlane is a local router for Codex on macOS that picks model and reasoning effort with Jev before each user turn, keeps native ChatGPT authentication, and records routing evidence locally. Shadow mode logs recommendations without changing execution.
Stars
2
Language
Python
License
MIT
Reading time
3 min
Published by
Community
Author
itscloud0
Last verified
Oct 2026

Highlights

  • Selects model and reasoning effort from your Codex catalog before a user turn, deciding between turns so one executor handles a turn's tool calls.
  • Shadow mode keeps the real executor and effort while recording what Effortlane would recommend; fresh installs default the CLI wrapper to Auto.
  • One-command install via install.sh; the installer asks for the decision-service key with hidden input and backs up your Codex configuration.
  • The README is explicit that subscription savings and quality gains are not yet proven; Codex CLI on macOS is the implemented path.
  • Local evidence records routes, cache counters and failures; effortlane native-shadow enable keeps Desktop and Remote native via documented hooks.

Quickstart

bash
curl -fsSL https://raw.githubusercontent.com/itscloud0/effortlane/main/install.sh | sh
~/.local/bin/codex --effortlane-shadow

Watch out

Grounded in the truncated README and GitHub metadata read on 2026-10-15. The README badges and install script point at a repository named effortlane while this manifest URL is codex-jev-native-router, and the project is labelled experimental: Desktop Auto is opt-in, and the external decision service may have its own cost.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.

FacebookClinicnotes

X: OpenRouter Decision Model Rankings

X: herdr + jev, an agent router

X: A group chat bot with decision room routing

From the Jev guides

Original write-ups on what this entry is for.

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai