{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"L E S S O N S - with Lennox Saint","title":"someone copied my Codex post — here’s what they missed","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/2bd4a0bb\"></iframe>","width":"100%","height":180,"duration":531,"description":"this is the actual build for a second Codex app that can run the AI models you choose.\nget the repo, every command and the copy-paste setup prompt free inside Codex Club: https://www.skool.com/codexclub\n\nsomeone copied my post word for word, including the same screenshot, so Episode Zero shows the method they left out.\n\nin the video, i build the three parts that make it work:\n- an isolated second Codex app on Mac, or separate profiles on Windows and Linux\n- a local proxy that translates the Responses API for other model providers\n- a model catalog for OpenRouter and Ollama\n\nOpenRouter gives you more cloud-model choice, but you still pay and your data travels. Ollama gives you a local, private and per-token-free path, but your hardware decides how usable it is.\n\nno magic. no “trust me.” just the build.","thumbnail_url":"https://img.transistorcdn.com/l89mKLJC9B274WBCQpbvr1KwqpBchcTpKDBQFMXC0qo/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9mYmIz/MGFhYjFjYzU1ODFm/ZGMxNTUyNjJhYmVj/YjE4Mi5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}