# lidge-jun/opencodex

> Local proxy server that translates Codex's Responses API into other LLM protocols (Claude, Gemini, Grok, DeepSeek, Ollama, etc.), supporting streaming, tool calls, reasoning tokens and images. It also manages a ChatGPT account pool for Codex with quota-based routing.

- Magnitude: 2.3 out of 10 — Steady
- Stars: 17,897 total · +39 stars measured 2026-10-25, 00:13–23:34 UTC
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-06-18 · Last push: 2026-10-25
- GitHub: https://github.com/lidge-jun/opencodex · Homepage: https://opencodex.me/ · Page: https://gitnova.dev/en/r/lidge-jun/opencodex

## Useful for

- Run Codex CLI with a Claude or Gemini model via the local proxy instead of OpenAI.
- Set up a ChatGPT account pool and rotate Codex sessions by quota in the web dashboard.
- Connect local Ollama or any OpenAI-compatible endpoint to Claude Code without changing the client.

## Why it’s here

- Star-counter measurements on 2026-10-25 (UTC), 00:13–23:34: 17858 → 17897 stars (+39). This is the change over that interval.
- About 7 forks a day — people are taking the code.

## Star trust

Star growth looks organic.
- Hardly anyone watches for updates: 23 watchers for 17,897 stars.

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

## Numbers

- Forks: 1,396
- Issues and pull requests: 7,652
- Watchers: 23
- Average over the last week: 53 per day
- Usual pace: 64 per day
- Latest release: v2.92.0 (2026-10-24)

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

2026-09-30 … 2026-10-29: 48, 53, 69, 57, 66, 55, 49, 70, 62, 60, 44, 48, 62, 48, 51, 44, 48, 53, 39, 78, 60, 52, 54, 33, 55, 35, None, None, None, None

## Magnitude by day, last 14 days

10-12 2.4, 10-13 2.4, 10-14 2.3, 10-15 2.8, 10-16 2.9, 10-17 2.8, 10-18 2.4, 10-19 2.5, 10-20 2.8, 10-21 2.5, 10-22 2.5, 10-23 2.4, 10-24 2.1, 10-25 2.4

---

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 2026-10-25 23:41 UTC, updated every 30 minutes.