Let's Go Christo!

RepoFinder

Turn a project and a goal into a short list of open source tools that genuinely fit - then interrogate every pick. Built entirely with OpenAI Codex on the OpenAI Responses API: gpt-5.6-luna extracts, gpt-5.6-terra ranks and explains, strict JSON Schema outputs, a labeled GitHub fallback, a remote MCP tool, 15 checked-in lessons on how Codex works, and a three-tier eval harness. One Cloudflare Worker, D1, plain HTML/CSS/JS.

Codex OpenAI Responses API MCP Cloudflare Workers D1 Evals Open Source

Give RepoFinder a GitHub repo or a public website plus a goal (“production evals”, “auth”, “background jobs”) and it returns three to five repos that genuinely complement your project - each with a What, a project-specific Why, a How to integrate, ease and impact ratings, and live GitHub evidence (stars, contributors, commits in the last 90 days). Then an “Ask OpenAI about this repo” chat lets you interrogate any pick: why it ranked, what the tradeoffs are, what else to consider. The point is the tagline: build better, focused, and faster - where your taste matters more than the number of stars.

It grew out of RepoRadar and Repo Recommender, and it is the lighter, sharper take: one engine serving two surfaces, a browser and a remote MCP tool at repofinder.io/mcp that any agent can call. The full build story - the model routing, the anti-hallucination guard, the checked-in lesson course on Codex - is in the write-up.

Share this post