# miuuyy/codex-chatgpt-web

> A bridge that lets you use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without spending Codex quota.

- Magnitude: 2.8 out of 10 — Steady
- Stars: 15,200 total · +8 stars measured 2026-10-29, 00:06–04:19 UTC, ≈ 64 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-07-26 · Last push: 2026-10-29
- GitHub: https://github.com/miuuyy/codex-chatgpt-web · Page: https://gitnova.dev/en/r/miuuyy/codex-chatgpt-web
- GitNova flagged it 10 days before GitHub Trending.

## Useful for

- Pick a ChatGPT Web model directly in Codex's model picker and continue the task
- Connect Codex MCP tools to ChatGPT via the OpenAI tunnel in full harness mode
- Run Zero Risk mode to paste prompts into ChatGPT manually without browser automation

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:06–04:19: 15192 → 15200 stars (+8). This is the change over that interval.
- Estimated end-of-day forecast: about +64 stars, using observed gains and the previous day.
- Top new repositories in the last 4 months: #35.
- About 9 forks a day — people are taking the code.

## 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: 1,203
- Issues and pull requests: 806
- Watchers: 43
- Average over the last week: 64 per day
- Usual pace: 108 per day
- Stars in the last hour (measured): 1
- Latest release: v6.1.15 (2026-10-29)

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

2026-09-30 … 2026-10-29: 163, 136, 104, 86, 93, 83, 84, 87, 95, 84, 85, 120, 91, 83, 82, 77, 86, 67, 77, 72, 80, 83, 73, 61, 46, 67, 70, 65, 74, 8

## Magnitude by day, last 14 days

10-16 3.0, 10-17 3.0, 10-18 2.8, 10-19 3.0, 10-20 2.7, 10-21 2.7, 10-22 2.9, 10-23 2.8, 10-24 2.5, 10-25 2.7, 10-26 2.9, 10-27 2.9, 10-28 2.9, 10-29 2.8

## Spotted in now

- Top new repositories in the last 4 months: #35

## More in this category

1. **HKUDS/DeepTutor** — 8.8 · Breakout · AI agents · Python · +415 stars measured 2026-10-29, 00:02–04:17 UTC, ≈ 1,933 by evening
   A lifelong personalized AI tutor with long-term memory: builds learning paths, reads documents and books, and runs practice and assessments via a multi-agent system and RAG.
   Full card: https://gitnova.dev/en/r/HKUDS/DeepTutor.md
2. **elayadesign/ai-design-skills** — 7.9 · Breakout · AI agents · +228 stars measured 2026-10-29, 00:02–04:17 UTC, ≈ 1,299 by evening
   A collection of markdown-based design skills for AI coding tools like Claude Code, Cursor, Codex and Windsurf, covering landing page design and turning static designs into animated showcases.
   Full card: https://gitnova.dev/en/r/elayadesign/ai-design-skills.md
3. **anonnerdfrenzy/survival-llm** — 7.7 · Early signal · AI agents · Python · +47 stars measured 2026-10-29, 00:02–04:17 UTC, ≈ 358 by evening
   A local offline LLM assistant with a library of ~1.5M survival, medical and how-to articles; every answer cites the exact source passage.
   Full card: https://gitnova.dev/en/r/anonnerdfrenzy/survival-llm.md
4. **unclebob/ub-mode** — 7.6 · Breakout · AI agents · +191 stars measured 2026-10-29, 00:02–04:17 UTC, ≈ 1,098 by evening
   An agent skill that enforces disciplined software engineering practices when writing or changing code: TDD, root-cause fixes, behavior testing, and quality gates via mutation testing. Installed as SKILL.md into the agent's skills directory.
   Full card: https://gitnova.dev/en/r/unclebob/ub-mode.md
5. **pbakaus/impeccable** — 7.6 · Breakout · AI agents · Rust · +551 stars measured 2026-10-29, 00:02–04:17 UTC, ≈ 2,466 by evening
   A set of commands and detector rules for AI coding agents that helps them produce better frontend design instead of generic templates. Installs as a skill into Claude Code, Cursor, Codex and other harnesses.
   Full card: https://gitnova.dev/en/r/pbakaus/impeccable.md

---

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 2026-10-29 04:27 UTC, updated every 30 minutes.