Build An AI Second Brain Knowledge Base (Step-By-Step)

Item: Build An AI Second Brain Knowledge Base (Step-By-Step)
Rating: 4
Author: PostSingularity Institute

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence

🎙 Matt Wolfe 👥 1.0M 📅 May 6, 2026 ⏱ 33 min 👁 169K 📄 tutorial 🧭 2026-08-28

Available in: English (current) Français

Keywords

second brainknowledge managementObsidianCodexAI wiki

Summary

Matt Wolfe presents a comprehensive tutorial on building an AI-powered second brain knowledge management system. The system is based on Andrej Karpathy’s LLM wiki concept, using Obsidian as the front-end for markdown files and Codex as the AI coding assistant. The video outlines three core pillars: a wiki/knowledge base for storing web content, a CRM for contacts and meetings, and a journal for daily reflections. The workflow involves using the Obsidian Web Clipper to ingest content into a raw folder, then prompting Codex to process and summarize it into a structured wiki with cross-links. The journal and CRM are integrated so that AI can ground responses in the user’s own knowledge base. The tutorial includes practical steps, such as configuring the web clipper, setting up the vault, and customizing the agents.md file. It also demonstrates querying the wiki and updating the system manually or via AI. The video concludes with a recap and mentions backing up to GitHub. The presentation is clear and methodical, making it accessible for users with basic technical skills.

173 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides high practical value by offering a concrete, actionable method to build a personal knowledge management system that leverages AI for organization and retrieval. The argumentation is solid, as it builds on a recognized concept (Karpathy’s LLM wiki) and demonstrates the process with real examples. The creator justifies each step, explaining the rationale behind the architecture and the benefits of interlinking notes. The demonstration of querying the wiki and receiving grounded responses illustrates the system’s effectiveness. The tutorial is well-structured, progressing logically from setup to advanced customization, and includes troubleshooting tips (e.g., adjusting the agents.md file). The argumentation is persuasive, showing how the system can transform information storage into an interactive knowledge base.

Scientific Rigor, Source Quality, Title Accuracy

The video demonstrates scientific rigor by crediting Andrej Karpathy for the original LLM wiki concept and providing a link to his GitHub page. The sources cited are relevant and reliable: Obsidian, Codex, and Karpathy’s gist. The tutorial is reproducible, with clear instructions and visual aids. The title accurately reflects the content, which is a step-by-step guide. The video does not overclaim; it presents the system as a personal productivity tool rather than a scientific breakthrough. The creator also acknowledges limitations, such as the need for manual adjustments. Overall, the sources are appropriate and the title-content alignment is strong.

228 words

Title / Content Match

The title accurately reflects the content: a step-by-step guide to building an AI-powered second brain knowledge base.

Quality & Reliability

8/10

The video provides a clear, step-by-step tutorial grounded in a well-known concept (Karpathy's LLM wiki) and uses reliable tools (Obsidian, Codex). The methodology is reproducible and the creator demonstrates practical results. However, the content is largely based on personal experience and the Karpathy reference, without independent verification or scientific rigor.

Chapters

Cited Sources

Karpathy's LLM Wiki GitHub Gist — Referenced as the basis for the wiki architecture.
Obsidian — Used as the markdown editor and vault for the second brain.
Obsidian Web Clipper — Used to save web content and YouTube transcripts into the vault.
Codex App — Used as the AI coding assistant to build and manage the system.

Concurring Sources

Karpathy's LLM Wiki GitHub Gist — The video explicitly builds on this concept, and the tutorial aligns with its architecture.

External References

Contribution & Novelties

The video’s original contribution lies in extending Karpathy’s LLM wiki concept with a journal and CRM component, creating a more holistic second brain system. It demonstrates a practical, step-by-step implementation using accessible tools (Obsidian and Codex), making the concept approachable for non-experts. The integration of journaling with the knowledge base allows for AI-grounded responses that draw on personal saved content, adding a personalized layer not present in the original wiki.

Pour aller plus loin :

Zettelkasten method — The interlinking note-taking method that inspired the wiki’s cross-linking approach.
Personal knowledge management — Broader context for the second brain concept.
Andrej Karpathy’s LLM wiki — The original concept that this video builds upon.

112 words

Radar Profile

The radar profile shows high scores in information quantity, quality, and reliability, with a slightly lower technical level. This indicates a well-balanced tutorial that is both informative and accessible, with a strong foundation in reliable sources.

Reliability 8/10

💬 Très positif. Sur les 30 commentaires analysés, la grande majorité exprime une forte appréciation, soulignant l'utilité pratique, la clarté du tutoriel et l'enthousiasme pour le concept, avec quelques suggestions d'amélioration.