Building a Custom Request Proxy for Claude and Cursor

samgoodwin89 · x · 2026-07-13

The author mentions having generated massive amounts of data using Claude and Cursor. In retrospect, their primary desire is to build a custom proxy layer to intercept and save every request. Over time, this would accumulate a vast amount of domain-specific data, potentially scaling to hundreds of millions or even billions of tokens.

The core idea is that heavy users of AI coding tools shouldn't just consume model outputs; they can also turn the interaction process into their own data assets.

Original post →

More from coding & agent

coding & agent channel →