{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "arahim3-kaggle-tpu-lab--wire-codex-cli-to-open-model",
 "repo": "ARahim3/kaggle-tpu-lab",
 "repo_url": "https://github.com/ARahim3/kaggle-tpu-lab",
 "repo_slug": "arahim3-kaggle-tpu-lab",
 "title": "Point Codex CLI at a Kaggle-hosted open model",
 "page_title": "How to point Codex CLI at a Kaggle-hosted open model with Kaggle Tpu Lab",
 "summary": "Use the public endpoint from a Kaggle TPU session as the backend for Codex CLI.",
 "who": "A developer who uses Codex CLI and wants to try an open model on their own code without a GPU.",
 "problem": "Codex CLI needs an OpenAI-style endpoint, and most open models are too large to run on a laptop.",
 "outcome": "Codex CLI sends requests to an open model on the Kaggle TPU and returns answers in the terminal.",
 "steps": [
  "Run the notebook for Qwen3.8-27B or GLM-5.3-Flash from the README table on Kaggle and click Run all.",
  "Copy the public URL and API key printed by the last cell.",
  "Open the model folder README (for example qwen38-27b/) and copy the exact Codex CLI lines.",
  "Fill in the URL and key from step 2 and start Codex CLI.",
  "Ask Codex CLI a small coding question and check that the answer comes from the endpoint."
 ],
 "agent_prompt": "In the ARahim3/kaggle-tpu-lab repo, read the Codex CLI lines in the <model> folder README, run that model's notebook on Kaggle, and configure Codex CLI with the printed URL and API key. Expected output: a Codex CLI answer to a test question served from the TPU. Verify the request reaches the Kaggle endpoint, not a default provider.",
 "agents": [
  "codex"
 ],
 "difficulty": "Beginner",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "The exact Codex CLI configuration lives in each model folder README, so follow the folder for the model you chose.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "A Kaggle account with TPU access, verified under Settings (phone number, and for some accounts a Persona identity check)",
  "Kaggle's free TPU quota, around 20 TPU hours a week",
  "For the terminal route: Python 3.9+ and the Kaggle CLI"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "The printed API key grants access to the public endpoint, so keep it out of shared config files."
  }
 ],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/arahim3-kaggle-tpu-lab/wire-codex-cli-to-open-model/",
 "md": "https://dedupedai.com/use-cases/arahim3-kaggle-tpu-lab/wire-codex-cli-to-open-model/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/arahim3-kaggle-tpu-lab--wire-codex-cli-to-open-model.json",
 "api_version": "v1"
}