A couple of months ago, I was approached by @romainhuet, OpenAI s head of developer experience, to join his team and help push my vision for building with these models on a scale that I could never achieve on my own. Of course, before agreeing to anything, my first request was to ensure the dedicated users of Repo Prompt, who supported my journey until this point, were taken care of. If you re reading this and you purchased an annual or lifetime license, check your inbox!
I've been an active user of Repo Prompt since I hunted it, and while I'm a little sad that it'll no longer be maintained, this bodes well for OpenAI Codex users.
Repo Prompt helps AI models understand your codebase without wasting tokens on irrelevant code.
Context Builder analyzes your project and selects the files and functions needed for your task, building dense context that fits in model limits.
It works with your existing AI subscriptions (Claude MAX, ChatGPT Plus, Gemini) — no extra API costs.
The MCP server turns Repo Prompt into a backend for Claude Code, Cursor, and Codex, giving them context analysis and discovery they can't do on their own.
In case you were looking for more insights on using Repo Prompt effectively, @masonjames (who previously reviewed the product) has a new video out that might help!
