{
  "id": 8459823,
  "title": "รัน local LLM ในแอป ChatGPT Desktop ด้วย opencodex ตัวเดียว",
  "url": "https://urgent.news/2026/09/19/local-llm-chatgpt-desktop-opencodex",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-19T12:39:22.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/sarantoon/ran-local-llm-ainaep-chatgpt-desktop-dwy-opencodex-tawediiyw-1cd"
  },
  "original_language": "th",
  "account": null,
  "summary": "A local Large Language Model (LLM) can now be run within the ChatGPT Desktop app using a tool called opencodex. Developed by Nokka, this open-source solution works as a proxy on your own computer, allowing you to interact with models like MiniMax M3, Qwen 3.8 27B, and GLM-5.3-Flash, rather than just OpenAI's models. The opencodex tool modifies the base URL in the app to point to a local proxy, enabling it to communicate with various models without requiring a fork or modification of the original app. This proxy service is MIT licensed and can work alongside the original Codex Desktop app, allowing for flexibility in choosing which models to use. The tool is easy to install and use, and it supports multiple runtimes, including Ollama, vLLM, and LM Studio.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}