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.

A collection of maths symbols for quick access:

• LaTeX
• Typst

These symbols can be used as is.

| Name | Type | Description | License |

Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)

These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.

Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.

My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.

This is a list of the most commonly used and relevant vtubing software. The "best" will always be subjective and depend on your specific requirements. Overall, the information in this list is as accurate as I could figure it out, but there might be errors or some details might become out of date. If you find anything that needs to be corrected, please let me know. You can also note it in a comment.

Additional explanations:

• iPhone means that an iPhone is basically required
• iFacialMocap support means that tracking data can be received from the iFacialMocap iPhone app
• VMC protocol means that the application can send and/or receive tracking data from other VMC protocol capable applications, allowing the combination of multiple tracking methods (e.g. VSeeFace receiving VR tracking from Virtual Motion Capture and iPhone/ARKit face tracking from Waidayo)
• Tobii means that the Tobii eye tracker is supported