Cascade Today: An All-in-One Layer for Claude Code
A month in, Cascade is a real product. What I learned about multi-model routing, hybrid retrieval (RAG, RRF, reranking), and improving a coding harness instead of replacing it.
Writing on software, open source, and technical deep-dives.
A month in, Cascade is a real product. What I learned about multi-model routing, hybrid retrieval (RAG, RRF, reranking), and improving a coding harness instead of replacing it.
macOS Screen Sharing is excellent, but it leaves one real privacy gap. The fix is simple, yet it usually hides behind pricey paid tools, so I built an open-source version in an afternoon.
Why I started building Cascade, and the first hard problems that showed up when you try to wrap a coding agent with your own tooling.
I have been experimenting with machine learning since 2016, from TensorFlow models to LLM-powered agents. Here is what actually works in production versus what stays in notebooks.
ClawDE is an AI development environment with a persistent Rust daemon at its core. Building it taught me where AI agents excel and where they still fall short.
I built nSelf because managed backend platforms kept raising prices and adding lock-in. Here is what I learned building an open-source alternative that deploys with a single command.
How I converted the C-based NREL Solar Position Algorithm to JavaScript while maintaining near-native performance and +/-0.0003 degree accuracy for solar calculations.
Building React applications for Fortune 500 clients taught me that the hard problems are never about React itself. They are about architecture, state management, and team coordination.
PHP has come a long way from its origins as a simple templating language. With PHP 7 and 8, it is now a genuinely fast, type-safe language powering serious enterprise applications.
Node.js did not just bring JavaScript to the server. It unified the entire development stack and created the largest package ecosystem in software history.