⏰ Current Time
🤖 Current Model
💪 Effort Level
🧠 Model Context
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.
| #!/usr/bin/env bash | |
| # claude-plugin-scope-fix.sh | |
| # | |
| # Workaround for Claude Code plugin scope bug (anthropics/claude-code#29240) | |
| # | |
| # When a plugin is installed at project/local scope, Claude Code's UI shows it | |
| # as "Installed" globally, blocking reinstallation at a different scope or in | |
| # other projects. This script manually edits the registry and settings files | |
| # to promote, add, or fix plugin scope entries. | |
| # |