0xNatoshi/jev-codex-router

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

AI agentsPython#ai#codex#jev#llm#macos

1.2 Early signal Magnitude out of 10. Star growth looks organic. Data as of September 20, 2026.

Open on Seismograph Open on GitHub

About the project

A local router for Codex that classifies each turn via Jev and picks the model, reasoning depth and speed mode. It plugs into an existing Codex Router install as a generic provider and saves about 60% versus a full-frontier baseline.

Useful for

Cut Codex costs by routing simple turns to cheaper models
Set up automatic fallback to GLM and deepseek when ChatGPT usage is exhausted
Collect a local decision log to calibrate the routing policy

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

0 stars so far today, about 13 expected by the end of the day.
The spike has held for 3 days in a row — not a one-off blip.
The repository is 3 days old and already has 71 stars.
Top new repositories this week: #188.
The repository is archived — the author no longer develops it.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 71
Stars in a day: 13
Forks: 7
Issues and pull requests: 0
Watchers: 1
Language: Python
License: MIT
Created: September 17, 2026
Last push: September 17, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 20, 2026Top new repositories this week: #185

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/0xNatoshi/jev-codex-router.svg?lang=en)](https://gitnova.dev/en/r/0xNatoshi/jev-codex-router)

Similar projects

8.6
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.

BreakoutAI agentsPython+2,144 stars in a day
8.2
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.

BreakoutAI agentsHTML+638 stars in a day
7.9
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

Early signalAI agentsPython+838 stars in a day
6.9
latent-spaces/brag
An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.

BreakoutAI agentsPython+489 stars in a day
6.6
Sac-Y/Jev-cu
Jev-cu connects Computer Use with the Jev model (TypeSafe System One): Jev picks the element, action, completion level and risk from textual UI candidates, while Codex Computer Use reads the interface and executes…

Early signalAI agentsJavaScript+212 stars in a day
6.5
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…

CoolingAI agentsTypeScript+604 stars in a day