LLM Wiki: A Knowledge Base Your AI Builds and Maintains


An LLM wiki is a folder of interlinked markdown pages that a large language model writes and keeps current from your raw sources — papers, notes, transcripts, data. Andrej Karpathy proposed the pattern as an alternative to retrieval-augmented generation: rather than re-deriving knowledge from your documents on every query, the model extracts it once, writes it down, and reads its own pages afterwards. The knowledge accumulates instead of being recomputed.

It is one of two ways to build the semantic layer of an AI knowledge base, and the pattern works. What it lacks is a view of its own structure. A model reading a wiki page by page has no measure of which concepts hold the material together, which topics have formed, or where the wiki is thin. InfraNodus adds that layer: it represents the wiki as a knowledge graph and reads its structure with network science, so the system can tell you not only what it knows but where it is not yet connected.

Set It Up

1
Create an Account

Sign up for a free InfraNodus account to get access to the knowledge graph tools and your API key.

Create a Free Account
2
Get InfraNodus MCP
https://mcp.infranodus.com

Add this URL as a connector via Settings > Connectors in Claude Web / Desktop and authenticate with your InfraNodus API key via OAuth.

3
Install the Skill
/plugin marketplace add infranodus/skills
/plugin install llm-wiki@infranodus-skills

Run these two commands in the Claude Code prompt to install the skill as a plugin (use infranodus-all@infranodus-skills to install all our skills at once). Or use npx in your terminal: 

npx skills add infranodus/skills --skill llm-wiki -g -a claude-code -y

npx comes bundled with Node.js. For ChatGPT and OpenClaw, see the full installation instructions.

Didn't work? You can simply download llm-wiki.zip from our GitHub repository and add it to your LLM client manually — see the step-by-step instructions.



Add Graph View to Your Knowledge Base

VSCode / Cursor Graph View Plugin Obsidian Graph View
An LLM wiki visualized as a knowledge graph in InfraNodus with topical clusters and gaps
An LLM wiki read as a knowledge graph: concepts as nodes, topical clusters in colour, gaps between them.

 

What an LLM Wiki Is


The structure is deliberately plain. Three folders and a linking convention:

raw/ immutable sources — PDFs, notes, transcripts, datasets wiki/ LLM-written pages — concepts, entities, summaries, comparisons output/ generated results — reports, analyses, drafts infranodus/ ontology files describing the structure of each wiki section

New material lands in raw/. The model reads it, extracts concepts, relations, and sources, and writes each of them as its own page in wiki/, connected with [[wikilinks]]. Ideas generated from those pages go to output/. When new sources arrive, the wiki is updated rather than rebuilt.

Because the linking convention is the Obsidian one, an Obsidian vault and an LLM wiki are the same folder. You can open it, navigate it, and edit it by hand — but you rarely need to. The model owns the markdown layer; you curate what goes into raw/ and decide what to ask.

This is the difference from a RAG pipeline. RAG embeds chunks, retrieves the closest ones, generates an answer, and discards everything. Cross-references made in one session are gone by the next, and as a chat grows longer its context becomes less relevant, so the results drift towards the generic. A wiki writes its conclusions down. They stay. The full comparison, including where a knowledge graph fits, is in RAG vs. LLM wiki vs. knowledge graph.


 

What It Cannot See


A wiki is still a pile of pages. The model can scan concepts and follow links, but it has no measure of the shape they form: which concepts are central, which clusters dominate, which parts of the material are barely connected to the rest. Every query starts from a local view.

This has a consequence that gets worse as the wiki grows. Each new page is written in the vocabulary of the pages already there, so the dominant topics keep being reinforced. The knowledge base becomes more coherent and more confident — and progressively less able to surprise you. Without a structural measure there is no way to tell a wiki that is maturing from one that is closing in on itself.

A knowledge base that only accumulates pages converges. What makes it generative is knowing where it is not yet connected.

You could ask the model to assess this. It will produce something plausible and different every time you ask. That is not a diagnosis, it's a guess about a structure the model cannot observe.


 

The Graph Layer


Represented as a network, the wiki becomes measurable. Concepts (or [[wikilinks]]) are the nodes, their relations are the edges, and the groups they fall into are topical clusters. Graph metrics then describe the structure directly: betweenness centrality identifies the concepts that hold the discourse together, community detection identifies the topics, and the sparse regions between communities are the gaps.

These come from a peer-reviewed text network analysis algorithm applied widely in network science, not from the model's impression of its own notes. Run it twice on the same wiki and you get the same answer — which is what makes it usable as a control signal rather than another opinion.

1 Topics and Central Concepts


The graph shows the dominant themes, their relative weight, and the concepts that act as conceptual gateways between them — nodes with high inter-topical influence relative to their number of connections. Those are the terms worth developing, because a small addition there propagates across the whole structure. It also shows which clusters carry only a few percent of the material: the underdeveloped areas and the patterns just beginning to form.

2 Content Gaps


A content gap is a pair of clusters that both exist in your wiki and are not connected to each other. The material contains both topics; nothing in it relates them. These are the blind spots — and they are the most productive place to work, because a question that bridges two established clusters produces something the material implies but does not yet state.

InfraNodus detecting content gaps in an LLM wiki inside Cursor
Gap detection running against a wiki folder from inside an IDE.

3 Ontology as Living Memory


Each folder of the wiki also gets an ontology file in infranodus/ — a flat list of relations in [[wikilinks]] syntax describing how its concepts connect. These files are appended to as new sources arrive, never regenerated from scratch, so they hold a current snapshot of the project's structure that is small enough to sit in context. The model reads the ontology to know where it is before it reads any page. This is the bridge between the markdown layer and the network view, and it is what turns a static folder into a memory the system can navigate. Give those relations explicit types and constraints and the ontology stops describing the wiki and starts steering the reasoning over it — see AI reasoning graph.


 

The Workflow


Build the wiki. Sources into raw/, the model extracts concepts and connections into wiki/, ontologies into infranodus/.

Read the structure. Map the concepts into a graph, identify the clusters and the conceptual gateways, and see which topics dominate and which are thin.

Run gap analysis. Surface the clusters that exist but are not linked, and the relations the material implies but never makes.

Ask across the gap. Instead of a general question, give the model the structure and a specific gap, and ask it to connect the two sides. The answer is targeted because the question was.

Each cycle adds pages, which changes the graph, which produces different gaps. The structure of the wiki becomes a feedback loop rather than an archive — the same dynamic described in cognitive variability and used deliberately in thought acupuncture.


 

From a Gap to a Question


Say the graph of a research wiki shows two well-developed clusters — financial flows and regression analysis — with almost nothing between them. The generic prompt would be:

Explain financial systems.

You already know what that returns. The structural prompt is:

Gap-driven question

How can regression analysis model financial flow dynamics?

The model now works on a specific conceptual bridge inside material it already has, which is why it produces a research direction rather than a summary. The gap did the hard part: it identified which question was worth asking. Repeated across the graph, this shifts the wiki from information retrieval to insight generation.


 

Visual or Programmatic


There are two ways to work with the graph layer, and they use the same data.

Visually, through the Obsidian graph view plugin or the VSCode / Cursor extension: explore clusters, click into nodes, see the gaps as you write. Useful when you want to develop a sense of the material's shape.

Programmatically, through the InfraNodus MCP server: the LLM runs the network analysis itself, reads the gaps, and acts on them without you looking at a graph at all. Useful when the wiki updates on a schedule and you want the research questions waiting for you.

Both work. Seeing the structure yourself gives you more control over which gaps are worth bridging — not every gap in a knowledge base should be closed, and some are worth widening.


 

Set It Up


The LLM Wiki skill scaffolds the whole structure for you, following Karpathy's specification with the graph layer wired in. It runs in Claude Code, Cursor, or any other client with skills enabled, and it is open source on GitHub if you prefer to adapt the template to your own conventions.

If you already keep notes in Obsidian, Roam, or Logseq, you can start from the graph side instead — see knowledge graphs for personal knowledge management. If you are starting from nothing, building a personal knowledge base covers the files, folders, and viewer first, and the AI second brain assembles the whole workflow.


 

FAQ

What is an LLM wiki?

A personal knowledge base of interlinked markdown pages that a large language model writes and maintains from your raw sources. Raw documents go into raw/, extracted concepts and relations into wiki/ as [[wikilinks]], generated results into output/. The pattern was proposed by Andrej Karpathy. ("LLM" here is large language model, not the law degree.)

How is an LLM wiki different from RAG?

RAG re-derives knowledge from your documents on every query and forgets the result. An LLM wiki does the extraction once and writes it down, so cross-references and syntheses survive between sessions. Retrieval still helps — GraphRAG against the wiki's graph is more precise than chunk similarity — but the wiki is the durable layer. Full comparison here.

What does InfraNodus add to Karpathy's LLM wiki?

The structural layer: network analysis of the wiki's own graph, showing influential concepts, topical clusters, and the gaps between them, plus an infranodus/ ontology folder that keeps a current snapshot of the project's structure as new sources arrive.

What is a content gap?

Two topical clusters that both exist in your knowledge base but are not connected to each other. Detected with community detection and betweenness centrality, so the result is reproducible rather than a model's guess.

Does it work with Obsidian?

Yes — the wiki is plain markdown with [[wikilinks]], so an Obsidian vault and an LLM wiki are the same folder. The graph view plugin adds the analysis inside Obsidian.

Can I use it as an AI second brain?

That is what it is. The difference from most second brain tools is where the work goes: they focus on capture and retrieval, this one measures the structure of what you have collected and tells you what is missing from it. See the AI second brain for the assembled workflow.


 

Build Your Own LLM Wiki


Connect your notes, papers, and data to a knowledge graph that shows you the topics, the central concepts, and the gaps between them:


Sign Up     Log In