{"id":7796,"date":"2026-07-08T23:04:54","date_gmt":"2026-07-08T23:04:54","guid":{"rendered":"https:\/\/learningaloud.com\/blog\/?p=7796"},"modified":"2026-07-08T23:04:55","modified_gmt":"2026-07-08T23:04:55","slug":"karpathy-plugin-for-obsidian","status":"publish","type":"post","link":"https:\/\/learningaloud.com\/blog\/2026\/07\/08\/karpathy-plugin-for-obsidian\/","title":{"rendered":"Karpathy Plugin for Obsidian"},"content":{"rendered":"
\n
\"\"<\/a><\/figure>\n<\/div>\n\n\n

I have spent a significant amount of time over the past week or so developing a Karpathy wiki<\/a> based on a large portion of my Obsidian notes. This process began in April when I decided to purchase a Macintosh Mini I intended to devote exclusively to the exploration of AI on the desktop. I was a bit slow in making this purchase and it took until last week to receive my purchase. My tardiness cost several hundred dollars more<\/a> than it would have a few months ago. <\/p>\n\n\n\n

I was motivated to invest and explore this area for two reasons. First, my main interest in AI continues to focus on retrieval-augemented generation (RAG<\/a>) of the notes and highlights I have collected to serve as a foundation for my writing projects. As I have used AI plugins to interact with the content I have stored and organized in Obsidian, I discovered that the API-based services<\/a> for interacting with these notes are relatively expensive because the process of first feeding the notes to the AI service must be repeated each time a session is initiated. Karpathy proposed that AI could be used to create a wiki based on the concepts and connections in a collection of source material, either once (when the collection was created) or as each new item of content was added, and this wiki could then be the focus of future explorations, reducing the cost due to the repeated input of the same content to the AI service. <\/p>\n\n\n\n

My second motivator was personal curiosity, sparked by the many posts promoting the potential of AI tools and models that could run on personal hardware, avoiding the costs and scrutiny associated with using online services from major AI companies. The proposal was that many common uses of AI no longer required access to $20 or $200-a-month subscription services.\u00a0<\/p>\n\n\n\n

I understand that another tutorial or \u201chow I did it\u201d post may be required at this point, but I read a post explaining that getting started with self-hosting LLMs will not be easy<\/a> as the posts newbies are likely to read make it sound, and a good deal of exploration and personalization will be required. The message was intended not to be discouraging but to communicate that \u201cdon\u2019t give up, you should be able to get it to work.\u201d This was pretty much my experience, and I thought it worthwhile to explain the issues I encountered and why I had to make adjustments to my specific situation. My experiences with tech since the mid 1980s have kind of gone this way. <\/p>\n\n\n\n

So, I have two Mac Minis now, and the first challenge was how to connect both to the same large monitor so I can switch back and forth as required by a general-use and a specific-use computer arrangement. I knew I would have to purchase a KVM (keyboard, video, mouse), but I had not considered that my current setup uses a Bluetooth mouse and keyboard. More specifically, Apple\u2019s Magic Keyboard and Mouse are not intended to be linked to more than one device. You charge your Magic keyboard with a USB cable, so the cable can be used as it has long been used to connect to a computer. You also charge your Magic Mouse, but the cable is inserted on the bottom of the mouse, preventing it from being used while it is being charged. Solution – purchase a mouse with a cable. The first challenge is overcome.<\/p>\n\n\n\n

My plan was to use the Obsidian Karpathy LLM wiki plugin because this seemed the most efficient way to create a working system. The plugin’s setup allows selecting multiple AI sources, including subscription services. I did use Anthropic\u2019s Claude API when I was having difficulty getting either of the two local options (Ollama or LMStudio) to work. Claude worked great, but adding one new source document cost 70 cents. My present collection is close to 300 note files, and the work the AI does increases as the complexity of the wiki increases so I treated the success as a sign the struggles I was experiencing could eventually be overcome. <\/p>\n\n\n\n

When using Ollama, I was experiencing a consistent problem with some, but not all of the note files the AI was ingesting to build the wiki. I spent a considerable amount of time over several days comparing the files that could and could not be processed and I never did find a difference. It wasn\u2019t the length, the presence of specific markdown tags, the tool I had used to create the original markdown file, or any other variable I could imagine. Nothing. However, the problem was consistent. The same files, time after time, would either work or fail. <\/p>\n\n\n\n

My typical strategy in such situations is to ask questions of the Internet. One proposal was that the JSON history had become corrupted. The solution was to reveal the invisible files (the .files and folders) and delete these files. New files would be generated when the Obsidian app was next launched. This was done without consequence.<\/p>\n\n\n\n

One issue I encountered was that the models displayed as options within Ollama did not contain the model (qwen2.5) I had found recommended when I read the descriptions of others. I searched how to add other models to Ollama and found it could be done with a terminal command (ollama pull <model name>. Now qwen2.5 appeared. Qwen3.6 was originally listed and I assumed there would be little difference, but for some reason, I was wrong, and the system worked with qwen2.5. <\/p>\n\n\n\n

\"\"<\/a><\/figure>\n\n\n\n

Without going into details because others have already provided tutorials, you first add and install the Karpathy LLM Wiki plugin for Obsidian. The gear icon associated with this community plugin provides a \u201cfill in the blank\u201d form where you enter information linking Obsidian to the AI online service or local option you want to use. <\/p>\n\n\n

\n
\"\"<\/a><\/figure>\n<\/div>\n\n\n

<\/p>\n\n\n\n

The wiki construction process is controlled by the commands that appear in the Obsidian command list when the Karpathy plugin is installed.<\/p>\n\n\n\n

\"\"<\/a><\/figure>\n\n\n\n

So, you start Ollama and select the model you will use in Obsidian. Start Obsidian and select the command to ingest a file or folder and be patient. Eventually, your wiki will be generated, and you can query the wiki rather than the source files. The right-hand column displays a response to a prompt.<\/p>\n\n\n

\n
\"\"<\/a><\/figure>\n<\/div>\n\n\n

<\/p>\n\n\n\n

So, I was able to generate a wiki based on more than 150 of my notes. In examining some of the components of the wiki I did find some weird artifacts. There were some with Chinese characters. I happen to be listening to LeoLaporte talking about different AI models and he said that qwen originated in China. It then made sense to me that the model might translate some of the Chinese names in my article summaries and include their Chinese translations (no idea if that is actually what happened). I also found some md pages with titles, but no content.<\/p>\n\n\n\n

When I used the Karpathy command to submit queries, I found the quality of the responses to vary. Some made sense and some ignored sources I knew existed and were central to what I expected. Rewording of the query in ways I thought the model should have understood as equivalent sometimes resulted in the response I expected.\u00a0<\/p>\n\n\n\n

The following comparison (first from querying my new wiki, and the second from using Claude with my original source files) demonstrates fairly substantial differences. As you can tell from a quick skim, there are significant differences in the eloquence and completeness of the responses. The sample responses are presented as an Appendix.<\/p>\n\n\n\n

Summary<\/strong><\/p>\n\n\n\n

Each user is likely to have a unique experience when applying a local AI system to their content to generate a Karpathy-style wiki. Expecting that it will take some tinkering is good advice even when following instructions or \u201chow to do it\u201d videos on YouTube. My effort here was to describe what this tinkering experience looked like. <\/p>\n\n\n\n

After at least getting the system to work, I was able to compare my first successful effort with what I generated for 44 cents using Claude. The differences were substantial.<\/p>\n\n\n\n

I assume there are many more issues to explore. I am currently repeating the process with a different script that instructs the AI on what to do when creating the wiki. If that effort produces substantial improvements, I will have to write another post.<\/p>\n\n\n\n

*******<\/p>\n\n\n\n

Response of local model to wiki<\/p>\n\n\n\n

Summary of Research Comparing Handwritten Notes vs. Computer Notes<\/p>\n\n\n\n

According to the literature summarized from various studies, there are several key findings regarding the comparison between handwritten notes and notes taken on computers:<\/p>\n\n\n\n

    \n
  1. Repetition in Note-Taking:<\/li>\n<\/ol>\n\n\n\n

       – A study by Bui et al. 2015 suggests that repeated exposure to material enhances learning outcomes, especially when coupled with effective note-taking strategies.<\/p>\n\n\n\n

      \n
    1. Handwritten Notes and Memory Retention:<\/li>\n<\/ol>\n\n\n\n

         – Longhand notes are described as more paraphrased and containing more signals and images, which can lead to higher text-related achievement when reviewed (from Longhand Notes).<\/p>\n\n\n\n

         – Lecture Note-Taking Strategies indicate that students who take notes by hand outperform those who use digital devices, as handwritten notes require a higher level of processing and engagement.<\/p>\n\n\n\n

        \n
      1. Editing and Revisions:<\/li>\n<\/ol>\n\n\n\n

           – Research by Mueller and Oppenheimer (2014) found that while typing is faster, it leads to less cognitive effort and thus less retention due to the lack of engagement required in handwriting notes.<\/p>\n\n\n\n

           – Follow-up revisions are crucial as they enhance memory retention. According to a study cited by AI response, revising digital notes can mitigate some of the disadvantages of digital note-taking, improving long-term recall and academic performance (from AI Response to Challenging Luo Study).<\/p>\n\n\n\n

          \n
        1. Professional Note-Taking:<\/li>\n<\/ol>\n\n\n\n

             – Additionally, in the context of professional training, effective note-taking is vital for future practitioners (from “Notetaking in Professions”).<\/p>\n\n\n\n

          References<\/p>\n\n\n\n

            \n
          1. Longhand Notes \u2014 Core mechanism explaining why handwritten notes are more beneficial.<\/li>\n\n\n\n
          2. Bui et al. 2015 \u2014 Effects of Repetition on Note-Taking and Recall Strategies in College Lectures.<\/li>\n\n\n\n
          3. “Notetaking in Professions”. Stacy and Cain, American Journal of Pharmaceutical Education (2015) \u2014 Importance of note-taking skills for professional training.<\/li>\n\n\n\n
          4. Mueller and Oppenheimer (2014) \u2014 Pen and Pad versus Laptop for Note-Taking.<\/li>\n\n\n\n
          5. AI Response to Challenging Luo Study \u2014 How Note Modification Research Might Counter Luo et al. (2018)<\/li>\n<\/ol>\n\n\n\n

            *******<\/p>\n\n\n\n

            Paste from Claude plugin within Obsidian<\/p>\n\n\n\n

            Handwritten vs. Computer Note-Taking: What Your Notes Say<\/p>\n\n\n\n

            Your vault contains extensive research on this topic, and the picture that emerges is more nuanced and contested than the popular narrative suggests. Here is a synthesis of what your notes reveal:<\/p>\n\n\n\n

            The Foundational Study<\/p>\n\n\n\n

            The most influential study is Mueller & Oppenheimer (2014), documented in Pen is mightier than the keyboard. Their key finding was that faster keyboard transcription led to more verbatim, less generative notes, while the slower speed of handwriting forced summarization and paraphrasing. Notably, their Study 3 found no differences when note review was not allowed, but longhand was superior when review was allowed\u2014a surprising result.<\/p>\n\n\n\n

            The Generative Processing Argument<\/p>\n\n\n\n

            Several of your notes outline the theoretical rationale:<\/p>\n\n\n\n