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.
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22