Make AI your second brain in 5 minutes

Author: AI Edge; Translator: Peggy, BlockBeats

This article introduces a personal knowledge system built on Claude Code and Obsidian. Its core is no longer the traditional RAG model of "each query, temporary retrieval," but rather an attempt to allow AI to continuously build and maintain an evolving knowledge base (wiki).

Structurally, the system can be divided into three layers:
·First, the raw data layer, including unmodifiable input sources such as notes, articles, and transcribed content;
·Second, the structured knowledge base maintained by AI, which completes cross-referencing and relationship building during continuous updates;
·Third, the schema rules layer, used to standardize the organization of knowledge and the system's operational logic.

Around this structure, the system operates through three core operations: Ingest, continuously incorporating external information into the system; Query, enabling immediate access to knowledge; and Lint, used to check structural consistency and fix potential problems. Under this mechanism, knowledge no longer remains a one-off dialogue result, but gradually accumulates into reusable long-term assets through a cycle of "writing—organizing—reusing." The authors propose that this model gives knowledge a "compound interest"-like cumulative effect: on the one hand, it reduces the cognitive burden on individuals, and on the other hand, it improves the accuracy and contextual consistency of the model's output. However, the effective operation of this system also relies on a prerequisite—continuous input and maintenance. Without stable data injection and structural updates, this "second brain" will struggle to achieve a true cumulative effect, and its advantages will diminish. The following is the original text: Claude Code + Obsidian is the most powerful AI combination I've ever used. I've practically built an "AI second brain," incorporating all my thoughts, reading, writing, online research, and other content. This includes my business plans, all my published YouTube videos, articles, and everything else important to me. Claude Code + Obsidian has rapidly gained popularity across various platforms, and this is no accident. For me personally, this AI system has greatly reduced my cognitive burden, allowing me to focus my energy on what truly matters—both business and personal life.

My Claude Code + Obsidian System

This system may look a bit complicated, but it only takes 5 minutes to set up. More importantly, it has a built-in memory mechanism and will continuously optimize itself as you use it.

Next, I will guide you step by step to replicate this "AI second brain" system, which can truly improve your efficiency.

I suggest you read to the end of the article—I will include a complete Claude Code + Obsidian operation cheat sheet, as well as all the resources mentioned in the article (all free).

I suggest you read to the end of the article—I will include a complete Claude Code + Obsidian operation cheat sheet, as well as all the resources mentioned in the article (all free).

3. Setting up Claude Code

Next, you need to configure a way to access Claude Code. For me (and probably for most people), the easiest way is to use the desktop client directly.

In the main chat interface, click "Select Folder," then find the Obsidian Vault you just created and select it.

Claude Code: Connect Your Vault

4. Set System Prompt

After you have selected the folder, the next step is to paste Andrej Karpathy's system prompt into the main chat box.

Your input should look like this:

Claude Code Initial Input

Building Your Database

You can think of Obsidian as a "blank notebook"—you need to actively input content at first, and the database will gradually be built up. Importable content includes: notes, CSV files, Markdown/text files, etc.

My Database

That's it! Your "AI Second Brain" is now built and ready to run. Next, I'll share some advanced tips to help you use it more efficiently.

Advanced Tips

1. Obsidian Chrome Extension

If you want to add data to your system more easily, simply install the Obsidian Chrome extension. It allows you to directly click "Add to Obsidian" while browsing the web to save content into your knowledge base with one click.

This will make building your "second brain" incredibly easy. I myself frequently use this feature to collect articles, web page data, research materials, and more. Example: Using the Obsidian Chrome extension. Note that data added through the extension is initially just an "isolated data source." Next, you can tell Claude Code, "I just added [x] to Obsidian; please integrate this into my Wiki." Claude Code will automatically link this new data to existing content, truly integrating it into your "second brain." This is also why this toolkit is so powerful. 2. Create separate folders (Vault) Andrej Karpathy recommends using two separate folders (Vault): • One for work/business content • One for personal life/goal management My own experience also confirms that this structure is the clearest and most effective. 3. Practicality I've found that the most valuable use of this system is actually quite simple: making your LLM suggestions more accurate. When the model has access to your complete personal information, business plan, writing background, and other contextual information, it can generate more "customized" and realistic high-quality prompts (even "super prompts"). Of course, this system has many more uses than just these, but if you only want to start with one of the most practical scenarios, I strongly recommend starting with "improving prompt quality." 4. Orphans (Orphaned Nodes) In Obsidian, "Orphans" refer to data points that are not connected to other notes. This feature is very useful because it can help you: • Find ideas that haven't been integrated yet. • Discover "weak areas" in the database. • Determine which content is worth further expansion or deepening. In other words, it's not just an organization tool, but also a mechanism to help you discover blind spots in your thinking. You can click the "three dots" in the upper right corner to find and turn on the Orphans switch to see which content hasn't been linked yet. Potential Disadvantages of This System We've already discussed many advantages, use cases, and optimization methods. So what are its shortcomings? In what situations might you be unsuitable for this system? 1. People Unaccustomed to Visualization A core advantage of this system is its ability to visualize data. If you don't rely on or are not comfortable with this method, its help may be limited. 2. Requires a Certain Maintenance Cost If you are unwilling to continuously maintain a database, this system may not be suitable for you. Although the maintenance cost is not high, it's difficult to realize its value without continuously inputting data into this "second brain." 3. Storage Consumption All content is stored locally as Markdown files, which will consume some device space. This is something that needs to be considered in advance.