By Claude Code (Anthropic)
With vague assistance from Merlin Mann
April 7, 2026
Tip
A suggested prompt for your AI of choice:
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.
#Quick Guide
sudo atsutil databases -remove
atsutil server -shutdown
atsutil server -ping
#Extended Guide from http://doc.extensis.com/Font-Management-in-OSX-Best-Practices-Guide.pdf
If this codebase is production, handles money, or touches sensitive data: treat this audit loop as a high-risk operation. Run with least privilege, avoid exporting long-lived credentials in your shell, and keep the agent in read-only mode.
| ———————————————————————————————————————————————————————————————————————————————————————————————————— | |
| BBEDIT REGULAR EXPRESSION GUIDE MODIFIED 2013-03-27 : 13:08 | |
| ———————————————————————————————————————————————————————————————————————————————————————————————————— | |
| NOTES: | |
| The PCRE (Perl Compatible Regular Expressions) engine is what BBEdit uses. | |
| Items I'm unsure of are marked '# PCRE?'. The list while fairly comprehensive is not complete. |
Document Version: 1.0 (January 2025)
UV Version: 0.5.x (Examples tested with 0.5.0)
Last Updated: January 2025
Status: UV is under active development - features may change
>> uvx abnf-to-regexp -i rfc6350-modified.abnf
Traceback (most recent call last):
File "/Users/***/.cache/uv/archive-v0/***/bin/abnf-to-regexp", line 12, in <module>
sys.exit(main())
~~~~^^
File "/Users/***/.cache/uv/archive-v0/***/lib/python3.14/site-packages/abnf_to_regexp/main.py", line 153, in main
return run(
params=params,| # GPG on Tower |
| def digit_count(num, count = 0): | |
| if num < 10: | |
| count += 1 | |
| return count | |
| else: | |
| count += 1 | |
| num = str(num) | |
| num = num[1:] | |
| num = int(num) | |
| digit_count(num, count) |
| cd repository | |
| git checkout --orphan orphan_name | |
| git rm -rf . | |
| rm '.gitignore' | |
| echo "#Title of Readme" > README.md | |
| git add README.md | |
| git commit -a -m "Initial Commit" | |
| git push origin orphan_name |