Field guide / primary domain

Obsidian

23

sources in this field

Updated July 16, 2026

Current thesis

The shortest path to orientation.

Obsidian is the dominant IDE for LLM-maintained knowledge bases, anchored by Karpathy's reference architecture: Web Clipper ingestion into a raw/ directory, a compiler generating .md files with backlinks and categories, and Marp for slide outputs. The community standard is now "vault as foundation, Claude Code as engine" — plain-text markdown that any agent reads directly, with LLMs writing and maintaining all wiki data while humans rarely edit it. Query results file back into the wiki, compounding future exploration. Two MCP servers—smart-connections for semantic search and qmd for structured metadata retrieval—bridge agent and vault. Agents solve the maintenance burden that killed historical wikis by noticing contradictions, flagging out-of-sync specs, and proposing structural changes; brain-ingest extracts 12-18 claims and frameworks from 90-minute audio locally. Shipping products now implement this pattern: Cabinet packages document processing and scheduled agents operating markdown workspaces; Tolaria (10,000-note proof point, 100K+ LOC, 85% test coverage) layers Git versioning and an MCP server atop plain markdown, designed as a shared human/AI environment; ByteRover unifies fragmented notes across tools into a relevance-scored index. The architectural consensus adds HTML artifacts as interactive interface layers above the markdown foundation for dynamic workflows. Excalidraw (110K stars, end-to-end encrypted) is now the de-facto diagram primitive for plain-text stacks. Google's Open Knowledge Format standardizes storage as interlinked markdown files agents can query and edit programmatically, potentially displacing Obsidian as the storage layer while workflow patterns persist.

Evidence board

Claims worth carrying forward
01

Knowledge systems fail because they optimize for input, not output. A vault without a feedback loop is 'a graveyard with good folders.' The fix is three mechanisms: frictionless capture (<10 seconds), a connection layer (Claude reading across notes), and a daily push of insights back to you.

02

Four-layer architecture: (1) Capture tools—Readwise, Airr, Whisper, Telegram bot; (2) N8N pipeline routing content into vault; (3) Obsidian as permanent markdown storage; (4) Claude as intelligence layer reading across everything. Each layer has one job; nothing overlaps.

03

Telegram-to-Obsidian quick capture: N8N workflow—Node 1: Telegram Trigger (message, bot_id); Node 2: Code node formats markdown (inbox/{{date}}-quick-capture.md); Node 3: Write File to vault /inbox/. Takes 30 minutes to build with Claude Code and N8N. Handles all phone captures permanently after that.

04

CLAUDE.md is the root-level context file Claude reads at session start. Required sections: Who I Am (name, work, focus, goals), Current Projects (active, stuck, next milestone), vault folder map, behavioral instructions (surface connections, challenge assumptions, flag contradictions), and current reading/obsessions. Update Current Projects and Reading sections weekly.

05

Daily brief prompt runs via N8N at 6am on a schedule: reads /inbox (last 24h) and /notes (last 7 days), outputs three things—(1) 3 specific connections between recent and older notes with quoted passages; (2) one pattern across the week's reading; (3) one question worth sitting with today. Saves to /inbox/brief-{{date}}.md automatically.

06

Weekly synthesis prompt asks Claude to identify: (1) emerging thesis forming in your thinking; (2) contradictions between recent saves and prior beliefs (showing both from your own notes); (3) knowledge gaps—what perspective is missing; (4) single highest-leverage action. Framed as 15-minute Monday session. This is where compounding actually occurs.

07

Five-folder vault structure designed to resist collapse: Inbox (raw captures), Notes (processed sources), Ideas (your own thinking), Projects (active work), CLAUDE.md (root). Rule: when in doubt, put it in inbox. Complex folder structures fail because categorization ambiguity raises capture friction until the system breaks.

08

Compound effect timeline: Month 1—useful tool. Month 3—Claude connects notes from 8 weeks ago to current problems you've forgotten. Month 6—full record of beliefs held and changed, patterns recognized before you consciously named them. Six-month head start is not closeable by working harder—only by starting earlier.

Adjacent fields

Key voices

Latest evidence

Recent additions

All synthesized insights →

CyrilXBT

How to Build an Obsidian Knowledge Vault That Gets Smarter Every Day Without You Doing Anything

A detailed 6-step system for building an Obsidian vault that auto-captures content via Readwise, Airr, Whisper, and a Telegram bot, routes everything through N8N pipelines, and uses Claude to generate daily briefings and weekly syntheses. The core thesis: knowledge systems fail because they optimize for input, not output—feedback loops (daily briefs, weekly synthesis) are what turn a dead archive into a thinking partner.

GREG ISENBERG

Design.md + AI Skills: Consistent Startup Branding in One Hour

Google's open-source Design.md format captures typography, colors, and spacing in a single markdown file that agents reference to produce consistent outputs. Combined with reusable skill files (landing page, mobile, pitch deck), it creates a design system any AI agent can apply uniformly across all surfaces—replacing the common pattern of polishing one screen while everything else looks generic.

Charly Wargnier

Tolaria: Open-Source Mac/Linux Desktop App for Human-AI Shared Knowledge Vaults

Tolaria is a free, open-source (AGPL-3.0) desktop app for Mac and Linux that implements Karpathy's LLM wiki concept — a shared knowledge environment for humans and AI agents. It uses plain markdown, Git-backed vaults, and includes a built-in MCP server for Claude Code integration. Built with Tauri, React, and Rust; 100K+ lines, 85% test coverage, 9.9/10 code health.

Dan McAteer

'Understand Anything' Plugin Turns Codebases (and Vaults) into Searchable Knowledge Graphs

'Understand Anything' is an open-source plugin for Claude Code, Codex, and OpenCode that analyzes a directory and builds an interactive knowledge base explaining structure rather than showing it. Notably, it generalizes beyond code — running /understand on an 888-episode Obsidian podcast vault (144K lines of markdown) produced a searchable knowledge graph.

Marie Haynes

Google Open Knowledge Format (OKF): Standardized Markdown for AI Agent Knowledge Bases

Google introduced OKF v0.1, an open specification formalizing the 'LLM-wiki' pattern into a portable, interoperable format. A bundle is simply a directory of markdown files with YAML frontmatter — no SDK, no schema registry, no proprietary tooling required. The single required field is `type`; everything else is optional. OKF targets the fragmented organizational context problem: schemas, runbooks, metrics, and join paths scattered across incompatible systems. Reference implementations include a BigQuery enrichment agent and a static HTML visualizer.

Moysei

Karpathy's Claude + Obsidian Second Brain: Full Setup Guide

A step-by-step guide to wiring Claude Code into an Obsidian vault as a self-maintaining knowledge engine, based on Andrej Karpathy's LLM Wiki pattern. The architecture separates immutable sources (raw/) from Claude-compiled linked pages (wiki/), uses MCP + Local REST API for vault access, and schedules daily maintenance at 7am. Key philosophy: start with 10 sources, delegate upkeep to the model, keep human judgment over curation.