Videos
Visual walkthroughs, conceptual code execution guides, and theoretical video essays.

A masterclass tutorial breaking down 10 core enhancements for file-based knowledge stores. Features an architectural breakdown contrasting the embedding mathematics of Vector RAG against the agentic compilation loops of LLM Wikis, alongside live setups for DataView dashboards, native Mermaid flowcharts, and background MCP Vault integration.

A step-by-step video guide walking through the setup of Andrej Karpathy's LLM Wiki pattern using Claude Code and Obsidian. Details setting up the vault folder structure, ingesting unstructured sources into interconnected concept notes, querying with cross-project synthesis, and contrasting compiled persistent memory against traditional runtime RAG.

A video analysis of how Pinecone Nexus maps to Andrej Karpathy's LLM Wiki pattern.

A video walkthrough showing how to build an active, self-improving personal knowledge base inspired by Andrej Karpathy's LLM Wiki pattern using Claude Projects. Demonstrates establishing a three-tier directory layout (raw sources, compiled wiki nodes, and outputs), structuring a librarian CLAUDE.md instruction file with index tracking, and setting up an automated health check maintenance skill.

A step-by-step video walkthrough showing how to build an active, compounding personal second brain using Obsidian, the Obsidian Web Clipper, and AI coding agents. Demonstrates clipping web articles and YouTube transcripts into raw storage, guiding autonomous agents to synthesize cross-referenced wiki notes, and navigating the resulting knowledge graph.

A technical workshop presentation by Paul Iusztin exploring how to build file-based Markdown knowledge graphs for agent long-term memory. Demonstrates multi-source ingestion pipelines (code repos, articles, YouTube transcripts), recurrence-based entity and concept extraction, deterministic Python indexing, and hierarchical progressive disclosure queries for Claude Code and Codex.
Build an OKF Brain Like Mine!youtube.comA practical video case study exploring a live implementation of Google's Open Knowledge Format as a sovereign personal memory engine. The walkthrough demonstrates an automated ingestion pipeline that splits inbound web references into atomic markdown concept nodes, uses persistent playbooks to guide downstream agent behavior, and leverages human-in-the-loop review boundaries to prevent data corruption.

A video presentation by Brace Sproul (LangChain) detailing the design of OpenWiki. Explains how codebase documentation optimized for AI agents differs from human docs, illustrating setup workflows, automated GitHub Actions updates, and agent integrations.

A video walkthrough demonstrating how to build a personal second brain and LLM Wiki in Obsidian using Claude Code. Covers directory setup, automated ingestion of unstructured notes, concept cross-linking, and Kanban boards for task management.

A practical video tutorial showing how to build an active second brain in Obsidian using Claude Code. Demonstrates ingesting multi-format sources (PDFs, URLs, YouTube videos), defining structured markdown schemas, and setting up automated routing rules to compile cross-referenced wiki notes.

A technical analysis of Google's Open Knowledge Format (OKF) and how it formalizes the Karpathy LLM Wiki pattern.

A high-level technical analysis of Google's Open Knowledge Format (OKF) specification. Explains how the standard formalizes the Karpathy LLM Wiki pattern into a cross-organizational directory structure of plain-text markdown files, enforcing strict YAML frontmatter metadata and atomic concept-splitting to optimize downstream agent traversal.

A technical walkthrough addressing scaling bottlenecks in file-based LLM Wikis. Demonstrates using Elasticsearch as a hybrid retrieval and storage backbone (dense vectors and BM25) to manage index bloat, reconcile updates across thousands of concept documents during ingestion, and serve sub-second context to agents with minimal token overhead.
How To Build LLM Wiki In Obsidian?youtube.comThe definitive video tutorial mapping out the core 3-tier local memory architecture, showcasing how to build a file-based ingestion pipeline, implement a Git-backed maintenance loop, and deploy an agentic vault firewall wrapper.

A deep dive video applying the Karpathy LLM Wiki pattern to private, multi-platform personal communication trails. Demonstrates how to write custom scripts to parse Google Takeout
.mboxarchives, agent logs, and.jsonlinteractive terminal loops into an air-gapped, local Obsidian twin, mapping the user's stylistic voice patterns and tracking operational frustration loops over time.
A video tutorial showing how to construct an AI-maintained Obsidian wiki using the Obsidian Web Clipper and Claude Code to capture, compile, and query interlinked markdown files.

A video guide showcasing how to implement Andrej Karpathy's LLM Wiki pattern in Obsidian using custom scripts.

A video guide showing how to build a self-evolving memory engine that compiles Claude Code logs into an Obsidian wiki.
I Trained an AI on Everything I've Ever Said Onlinem.youtube.comA detailed implementation video showing how to ingest personal multimedia histories into a Karpathy-pattern local wiki. Integrates OpenAI's Whisper and Claude Code to parse raw video transcripts and JSON archives, compiling the data into a flat Obsidian folder topology (
concepts/,entities/,sources/) utilizing automated meta-logging hooks and structural schema policies.
A practical video tutorial demonstrating how to build an AI second brain and operating system inside Codex using GPT-6 Astra. Explores the "Four Cs" framework (Context, Connections, Capabilities, Cadence), configuring AGENTS.md, compiling linked Markdown wikis, and establishing structured memory routing loops.

A video presentation by Jacob Teo (Cognition) explaining the scaling architecture of DeepWiki. Discusses codebase graph scaling, path compression, and heuristics for compiling developer documentation to ground Devin.

A video walkthrough introducing OpenWiki, demonstrating how it compiles Git logs and comments into a codebase wiki.

A deep-dive 30-day technical review tracking a 760-page agent-managed knowledge vault built on top of Quartz. Explores the explicit scaling limits of the pattern, detailing the setup of background monitoring crons, automated append-only ledgers, and strict linting rules that treat uncited text blocks as structural pipeline errors.

A comprehensive beginner video guide walking through the end-to-end setup of a local Obsidian and Claude Code LLM Wiki. Covers creating the three-layer directory structure (raw/, wiki/, schema), writing CLAUDE.md operating guidelines, automating raw document ingestion, exploring concept connections in graph view, and running periodic health linting routines.

A practical video guide on bootstrapping an LLM Wiki from scratch inside Claude Code, demonstrating automated multi-agent ingestion loops, backfill routines for external web research, and visual chart integrations.

A technical video analysis comparing write-time synthesis in Karpathy LLM Wikis against query-time synthesis in structured database memory systems like Open Brain. Examines the editorial trap, semantic drift, and concurrency failure modes in multi-agent environments, proposing a hybrid architecture that pairs immutable database sources of truth with dynamic compiled wiki views.

A video walkthrough and demo of Kompl, an open-source compounding LLM Wiki. Demonstrates compiling source documents into an interlinked wiki with claim-level citations, interactive topic maps, disagreement tracking, and agent retrieval over an 8-tool MCP server.

A presentation from the AI Engineer World's Fair 2026 detailing how to construct high-reliability agent knowledge bases. Outlines standardizing on plain Markdown raw directories, enforcing strict source-grounding where claims are one click away from their references, utilizing controlled vocabularies and tag ontologies, and deploying the Hubble open-source note-taking app to host agent pipelines.
LLM Wiki: Your Mind, Structured by AI (Maria Martinez Miralles at Thoughtworks XConf Europe 2026)youtube.comA conference presentation detailing the shift from ephemeral RAG prompts to persistent, compounding LLM Wikis. Outlines separating immutable raw sources from agent-maintained Markdown pages, establishing schema rules, automating entity cross-linking, running periodic health linting routines to resolve contradictions, and preserving query synthesis as durable artifacts.

A discussion featuring Harrison Chase, Brace Sproul, and Devin Stein on the design and efficiency of LLM Wikis.

A developer-focused video guide walking through an automated, local-first ingestion and compilation architecture for flat-file wikis. It demonstrates how to combine on-device voice transcriptions and web clippers into an unformatted raw data directory, details a background cloud runner script using Docker and headless Obsidian sync to dynamically enrich metadata via markdown-based master tags, and highlights building custom HTML/JS interactive graph visualizations over native wiki-link topologies.

A step-by-step video setup walkthrough for Open Brain (OB1). Demonstrates provisioning the core PostgreSQL/Supabase database with pgvector, configuring the AI gateway, establishing the remote MCP server connection for AI agents (Claude, Cursor, ChatGPT), and preparing the infrastructure for wiki compilation recipes.

An update video announcing OpenWiki 0.2's adoption of the Open Knowledge Format (OKF) specification for wiki metadata.

A walkthrough introducing OpenWiki 0.1.0, showing how to configure a personal brain with Notion and Gmail connectors.

A walkthrough of Google's Open Knowledge Format (OKF) standard for organizing information into sovereign, flat-file markdown vaults.

A comprehensive technical walkthrough breaking down a file-driven AI memory architecture. The presentation details how to construct an intentional three-layer LLM Wiki using flat markdown directories and a central YAML indexing schema to completely bypass vector database complexity while enforcing an ultra-token-efficient agent retrieval loop.

A video tutorial detailing a human-in-the-loop (HITL) trust architecture for LLM Wikis in Obsidian using Hermes Agent. Adapts the Medallion data lake pattern (Bronze/Raw to Silver/Review to Gold/Wiki) across three implementation paths: Hermes' built-in skill, a Review Companion skill using Markdown proposals, and a full Agentic Librarian with deterministic verification tools.

A visual guide explaining the mechanics of nodes, edges, and triples, the token-efficiency of GraphRAG over standard RAG, and a workflow for sandboxing human vs. agentic Obsidian vaults.
