# 0xNatoshi/jev-codex-router

> 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.

- Magnitude: 0.1 out of 10 — Steady
- Stars: 274 total · +0 stars on 2026-10-04 (UTC), ≈ 0 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · License: MIT · Created: 2026-09-17 · Last push: 2026-09-22
- GitHub: https://github.com/0xNatoshi/jev-codex-router · Page: https://gitnova.dev/en/r/0xNatoshi/jev-codex-router

## 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

## Why it’s here

- The repository is 17 days old and already has 274 stars.
- The repository is archived — the author no longer develops it.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 43
- Issues and pull requests: 13
- Watchers: 1
- Average over the last week: 1 per day
- Usual pace: 16 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-06 … 2026-11-04: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-21 4.1, 09-22 4.3, 09-23 3.8, 09-24 3.0, 09-25 0.8, 09-26 0.4, 09-27 0.3, 09-28 0.4, 09-29 0.4, 09-30 0.3, 10-01 0.1, 10-02 0.1, 10-03 0.1, 10-04 0.1

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-04 00:26 UTC, updated every 30 minutes.