Tutorials and Setup Guides
Practical setup walkthroughs, implementation blueprints, and step-by-step guides for constructing personal vaults.

A step-by-step setup guide for building a personal LLM Wiki, outlining the three-layer vault architecture (raw sources, wiki nodes, and CLAUDE.md guidelines) managed via the Claude Code terminal agent and visualized in Obsidian.

An advanced guide transitioning the LLM Wiki pattern from interactive commands into an automated background operating system. Details how to orchestrate automated morning briefings and evening debriefs using Anthropic Cloud Routines, steer background agents with structured priority maps, and integrate live external context using Google Calendar and Gmail MCP servers.

A step-by-step guide to building a persistent, compounding markdown wiki using Claude Code and Obsidian on Windows. Outlines schema rules, ingestion pathways, and automated maintenance loops.
Beyond RAG: How I built a serverless AI LLM Wiki engine using OKF and AWS RODA (visrow Medium)medium.comA guide on building a browser-based, serverless OKF wiki compiler using WebLLM and AWS Registry of Open Data.

A step-by-step tutorial on constructing a Karpathy-inspired personal knowledge base using Claude Code over local Markdown. Details setting up the three-layer layout (raw sources, living wiki pages, and CLAUDE.md schema rules), advises starting small with a single domain to avoid migration churn, and explores relying on direct context-window reasoning over an active index for vaults under 100k tokens.

A practical implementation blueprint executing the LLM Wiki pattern using Claude Code as a vault maintainer. Demonstrates how to configure text-based slash commands (
/ingest,/query,/lint,/log) to manage the boundary lines between raw input stores and compiled concept nodes while establishing hard citation tracking across file line coordinates.
An implementation guide introducing the open-source
myKGlibrary to enforce type-safe ontologies in local vaults. Demonstrates how to run automated pipeline integrations for Claude Code using terminal skill configurations, establish explicit source traceability records, and configure numerical confidence tracking metrics to eliminate silent agent hallucinations.
A practical implementation guide and prompt template for domain practitioners and citizen developers to build a Karpathy LLM Wiki using Claude. Details a three-layer directory layout, a complete ready-to-run CLAUDE.md schema prompt, a three-session onboarding workflow, and starter kits for insurance, finance, and automation domains.

A practical implementation walkthrough on building a local-first Karpathy LLM Wiki using OpenKnowledge and AI coding agents. Covers schema setup (
external-sources/,research/,articles/,index.md,log.md), MCP bridging to Claude Code and Cursor, and executing automated ingestion, cross-linking synthesis, and continuous vault linting passes.
Building an LLM Wiki, Part 1 (Erik Evenson Blog)erikevenson.netA guide explaining how to implement the basic Karpathy pattern using Obsidian, its Local REST API, and Claude Code.
Building an LLM Wiki, Part 2 (Erik Evenson Blog)erikevenson.netAn article detailing schema linting, staleness detection, contradiction handling, and search testing for LLM Wikis.

An implementation guide detailing how to build a standalone TypeScript CLI (
wiki-cli) using Bun and the Claude Code Agent SDK. Explains how to synthesize knowledge on write over plain Markdown and JSONL logs, hook into agent sessions for silent two-phase auto-capture, configure schema-based quality bars, and automate self-healing health checks withwiki lint --fix.
Building an Offline-Local, Multi-Vault LLM Wiki for Obsidian (Paul Hackenberger on Medium)paul-hackenberger.medium.comA practical implementation guide for constructing a private, offline multi-vault LLM Wiki in Obsidian. Details an air-gapped local AI stack (Qwen for reasoning and conflict resolution, Gemma for vision, and DeepSeek-OCR-2 for PDFs via oMLX), a two-layer directory layout separating raw inbox drops from living wiki nodes (
concepts/,persons/,timeline.md,index.md), automated/wiki-syncingestion with source citations, cross-vault synthesis via/wiki-report, and a TypeScript lifecycle hooks plugin (commandHooks.ts).
A practical walkthrough for converting conversational ChatGPT data exports into a compounding Karpathy LLM Wiki using Claude Code and Obsidian. Outlines parsing non-linear message trees from
conversations.jsoninto linear Markdown files underraw/chatgpt/, structuring vault schemas inCLAUDE.md, and running automated ingestion loops that synthesize accumulated insights into atomic, cross-linked concept nodes with provenance citations.
A code-level implementation guide detailing the software architecture of the
llm-wiki-compilerengine. Walks through the step-by-step orchestration of a multi-model text compilation loop, local workspace linting rules, and inline source-provenance tracking without vector databases.
Hermes LLM Wiki: How to Set Up Karpathy's LLM Wiki in Hermes Agent (Julian Goldie on Goldie Agency)goldie.agencyA practical setup walkthrough for running Karpathy's LLM Wiki pattern using Hermes Agent and its bundled
llm-wikiskill. Details directory layouts (SCHEMA.md,entities/,concepts/,queries/), automated ingestion and linting routines, pairing with Obsidian, and setting up headless continuous synchronization viaobsidian-headless.
A technical guide explaining how Row-Bot compiles local-first memory into an Obsidian-compatible wiki graph.
How to Build a Second Brain You Can Actually Trust Using myKG and Obsidian (Senol Isci on Medium)medium.comA guide addressing facts and hallucination risks when extracting knowledge graphs with LLMs. Introduces myKG configurations using confidence-scoring metrics, strict source attributions, pre-extraction schema validation gates, and tunable trust thresholds to build verifiable personal Obsidian wikis.
How to Build an AI Brain That Never Forgetssaranfn.substack.comA practical implementation blueprint detailing how to build an air-gapped, local Obsidian memory vault. Walks through extracting conversational data streams from proprietary web platforms, configuring root-level orchestration instructions (
CLAUDE.md), and deploying background automation scripts to sync data sources and log daily workflow progress.
A guide adapting the CODE and PARA frameworks for AI workflows, highlighting knowledge decay, semantic auto-linking, and Model Context Protocol (MCP) integrations.
How to Build an LLM Knowledge Base (DAIR.AI)academy.dair.aiA practical workshop guide defining a standard local directory architecture and outlining repeatable agentic compiler patterns.

An architectural guide and implementation blueprint detailing a disciplined operating contract for LLM Wikis. Outlines deterministic intake with source manifests and content hashes, structured page types (
topics/,entities/,decisions/,contradictions/,candidates/), diff-producing ingestion passes, and an answer writeback protocol.
A three-phase implementation blueprint constructing an LLM Wiki as a file-based knowledge graph. Explores 2-source recurrence thresholds for entity and concept promotion, Open Knowledge Format (OKF) frontmatter schemas, deterministic Python index generation, a 3-step progressive disclosure query ladder, and multi-source ingestion adapters.
How to Build Karpathy's LLM Wiki: The Complete Guide to AI-Maintained Knowledge Bases (Dylan Boudro on Starmorph)blog.starmorph.comA comprehensive setup walkthrough detailing the three-layer LLM Wiki architecture, outlining the ingest/query/lint workflows, and providing a production-ready CLAUDE.md schema template for Obsidian and Claude Code integration.
How to Build Your Agentic Knowledge Base (after 16 months of running my own) (Chris Lettieri on Bits of Chris Substack)bitsofchris.comA practical implementation guide outlining a three-layer folder structure (inbox, notes, map) to let a knowledge vault taxonomy emerge organically, detailing the standard eight components of agentic vaults and the scaling progression path.
LLM Knowledge Bases (DAIR.AI)academy.dair.aiA detailed breakdown of the four-phase compilation pipeline (Ingest, Compile, Query, Lint) with architecture diagrams and implementation workflows.

A practical implementation guide and starter template breaking down the three layers (sources, wiki, schema) and core operations (ingest, query, lint) of Karpathy's LLM Wiki. Includes a copy-pasteable CLAUDE.md/AGENTS.md schema for Claude Code or Codex, an Obsidian setup walkthrough, and an architectural analysis of team scaling bottlenecks.

A three-part implementation series on building a minimal Markdown knowledge base and maintaining it with agents.

The second part of a practical series exploring how to visualize and inspect compiled Markdown wikis inside Obsidian.

The third part of a series outlining how to transition static Markdown wikis to autonomous agentic maintenance workflows.
LLM Wiki for Notion: Building a Claude-Powered Second Brain with a 3D Knowledge Graph (IVGraph)ivgraph.comA guide on building a Claude-powered LLM Wiki from Notion databases using MCP and 3D knowledge graph visualizations.

A practical setup guide for implementing Karpathy's LLM Wiki pattern in an Obsidian vault. Details folder layout, attachment routing, writing schema contracts (SCHEMA.md, CLAUDE.md, AGENTS.md), configuring maintainers (Claude Code, Hermes Agent, Obsidian plugins), and tailoring graph view filters for knowledge auditing.
LLM Wiki Local (Local LLM) (Part 2 of 3)medium.comA tutorial on configuring a fully local-first LLM Wiki using llama.cpp and Opencode on Windows. Demonstrates manual environment wiring, setting up AGENTS.md instructions as standard operating procedures, and deploying custom scripting gates to manage local data compilations.

A tutorial on constructing a hybrid ingestion engine for local LLM Wikis on Windows. Focuses on resolving formatting issues with large PDF documents using a custom Python script (the PDF Bridge) and routing local traffic via the Bifrost gateway.

A technical walkthrough and architectural analysis of the nashsu/llm_wiki desktop application. Details its two-step chain-of-thought ingest pipeline, Louvain community graph clustering, LanceDB vector search, and four-phase context-assembly retrieval pipeline.

A comprehensive setup guide and technical walkthrough for the cross-platform Nash Su LLM Wiki desktop application. Details its two-step chain-of-thought ingestion pipeline (analysis pass and file generation), Obsidian-compatible vault layout, Louvain community knowledge graph, optional LanceDB vector hybrid retrieval, and local HTTP API.
Readers Asked for My LLM Wiki Skill. Here's a Template You Can Make Your Own (Mark Chen on Medium)medium.comA practical tutorial and customizable template for building an LLM Wiki using Claude Code. Outlines a beginner-friendly three-layer architecture (immutable sources in
raw/, model-maintained markdown inwiki/, and steering rules inCLAUDE.md), detailing repeatable ingest, query, and linting procedures while preserving human curation oversight.
A configuration guide detailing how to build a git-hook-triggered pipeline to keep an OKF knowledge graph in sync. Demonstrates how to automatically compile, link, and lint repository context with every commit to serve pre-warmed context to agents.
Supercharging LLM Wiki with Knowledge Graphs: Build a Self-Evolving Research Systemsupport.noduslabs.comA guide and video tutorial detailing how to integrate network analysis and knowledge graphs into an LLM Wiki. Uses InfraNodus and Obsidian to identify conceptual clusters, map structural gaps, and direct agents (via custom skills in Claude Code) to formulate research questions that resolve disconnected topics.

A guide on scaling the LLM Wiki pattern to organizations, detailing tool-native ingestion and drift detection.

A practical setup walkthrough and workflow guide for running the Karpathy LLM Wiki skill on Buda AI. Details the separation of immutable raw sources and compiled markdown articles, cascading updates for disputed and outdated claims, read-only query routing, and evidence verification via
check_evidence.py.
A configuration guide detailing how to implement Andrej Karpathy's LLM Wiki pattern in the Kiro AI IDE. Explores configuring three-layer vault directories, defining system steering instructions, automating raw source ingestion via fileCreated event hooks, and running one-click health linting to prevent structural drift.

A tutorial and architecture case study demonstrating how to feed live web search and structured extraction directly into an LLM Wiki compilation pipeline. Uses Claude Code agent skills to compile multi-source research into an Obsidian-compatible markdown vault (
~/.nimble/memory/), illustrated with domain vaults across tech ecosystem intelligence and healthcare market analysis.
What Is Andrej Karpathy's LLM Wiki? How to Build a Personal Knowledge Base With Claude Code (MindStudio Blog)mindstudio.aiA beginner-friendly tutorial for setting up a local Obsidian vault and querying it using the Claude Code terminal client.

A guide on building an AI Research OS memory layer to compile notes and web sources into a queryable wiki for agents.
