A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

This document details the modifications required to run the Google Antigravity extension (google.google-antigravity@1.5.0+) inside Eclipse Theia / Theia-based IDEs instead of upstream VS Code.

Out of the box, Antigravity fails to load inside Eclipse Theia due to structural differences between the VS Code webview subsystem and Theia's architecture:

Ask questions and see you on November 2 at 8pm CET: youtube.com/c/bienadam

Also check out the latest episode:

Please keep your questions as short and as concise as only possible. Feel free to ask multiple, shorter questions. I will also answer some questions in my "shorts" on youtube.com/@bienadam/shorts between the shows.

Code is clean if it can be understood easily – by everyone on the team. Clean code can be read and enhanced by a developer other than its original author. With understandability comes readability, changeability, extensibility and maintainability.

1. Follow standard conventions.
2. Keep it simple stupid. Simpler is always better. Reduce complexity as much as possible.
3. Boy scout rule. Leave the campground cleaner than you found it.
4. Always find root cause. Always look for the root cause of a problem.