YOUR OBSIDIAN VAULT READS ALL 2,000 NOTES TO ANSWER... ONE QUESTION. THAT'S NOT A SECOND BRAIN. That's a hoarder with markdown files. Hundreds of thousands of tokens burned per answer, and it still grabs the wrong note half the time. A real second brain runs on a graph: a router, an index, nodes, edges. Fable 5 reads 2-3 files instead of the whole vault. Answer back in under a second. The graph view everyone screenshots in Obsidian is a poster. The index is the actual engine. Full 11-step build below, from raw vault to working graph 👇show more

THIS IS WHAT YOUR SECOND BRAIN SHOULD LOOK LIKE... most people dump notes into obsidian and call it a second brain it’s not a second brain it’s a second drawer karpathy just dropped the pattern that changes this and it’s called the llm wiki every time you add a source ai reads it, extracts key claims, updates every connected note and flags contradictions your obsidian stops being an archive and starts being alive save this and show it to someone still using notion as a second brain full breakdown in the article ↓show more

HE BUILT A 100% PRIVATE SECOND BRAIN IN OBSIDIAN... TO AUTOMATE HIS RESEARCH USING HERMES AGENT AND NOTEBOOKLM He visualizes his entire knowledge graph on-premise without paying for cloud subscriptions By connecting Hermes Agent and NotebookLM, developers can index hundreds of documents and generate content locally Four components of this local knowledge architecture: 1. Memory layer - set up an Obsidian PARA vault to store markdown notes and profiles 2. Agent layer - connect Hermes Agent to write files and run background scripts 3. Synthesis layer - use NotebookLM to create structured overviews from raw transcripts 4. Automation layer - trigger cron tasks to synchronize files and calendar standups The setup saves over $4,000 annually while keeping all private files offline Get the full step-by-step configuration guide and setup commands in the article below ↓show more

THIS DEVELOPER USED A 10,000+ STAR OBSIDIAN REPO TO... TURN HIS GROWING VAULT INTO A SEARCHABLE AI MEMORY SYSTEM most people keep adding notes until the graph looks impressive but nobody can find the exact context when a real task starts new note → ai summary → entity links → backlinks → graph update → claude retrieves the right 3–5 files instead of scanning the entire vault the system connects projects, decisions, research, and unfinished ideas, so old context resurfaces automatically instead of disappearing inside hundreds of folders he built the workflow around Claudian, an open-source repo with 10,000+ GitHub stars that brings Claude Code directly into Obsidian → bookmark this before your next 1,000 notes become another beautiful graph that your AI still cannot useshow more

I gave my Obsidian vault a lawyer's brain and... now it argues with itself before it answers me three months ago I was drowning. 20 government acts, budget docs, constitutions, all sitting in my vault as dead markdown I could never actually query. so I stopped treating it like notes and built it a nervous system I turned it into a 10-node graph. every question I ask hits a router first. it decides in a split second: is this a greeting, is this garbage, is this vague, or is this real. greetings die for free. garbage gets rejected. and if my own question is too vague, the vault stops and asks ME to clarify before it wastes a single token then comes the part I'm proudest of. after it writes an answer, a second node reads that answer back against the actual chunks it pulled from my vault. if the answer isn't grounded in what I actually wrote, it kills it. my vault would rather say "I don't know" than lie to me. it physically cannot hallucinate I compressed 20+ dense documents into 15,408 chunks, cut the vectors by 75% so storage costs almost nothing, and cached everything so repeat questions come back in under 100 milliseconds I used to have a folder of files. now I have something that thinks before it speaks, checks itself before it answers, and refuses to make things up about my own life. that's the difference between storing knowledge and building a mindshow more

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE FABLE 5 +... OBSIDIAN Andrej Karpathy (openai co-founder) shared an architecture that turns Claude into a persistent second brain instead of a basic chat window how it works: > you point Claude Code at an Obsidian vault folder > you drop articles, PDFs, or video transcripts into raw folders > Claude reads the files, updates topic summaries, and cross-references everything > the knowledge base compounds like interest instead of resetting on every new chat the setup is simple: > install and create a local vault directory > open the directory in Claude Code and paste Karpathy's wiki prompt: > > let the agent generate raw, wiki, and CLAUDE.md schema directories > drop any text file into raw and tell the model to ingest it > ask questions across the whole vault and query compiled summaries this eliminates rag database overhead and keeps your local vault organized how do you manage your local knowledge base?show more

A Harvard sophomore pointed Claude Code at his Obsidian... vault and woke up to 1,847 notes he never wrote. The vault started in September 2024 with 210 notes lecture scraps, 4 problem sets, 3 half-finished essays and by March it was dead, because nobody links notes by hand at 2 AM. So he handed the folder to an agent: read access to 210 files and one instruction, find what connects. It ran for 6 hours and built edges he'd never seen, wiring a thermodynamics lecture to a supply-chain note to a Douyin livestream case study he saved in 2023 and forgot. Graph view at 4 AM showed 1,847 nodes and 11,400 links, a white sphere so dense the center goes solid. His midterm was 9 days out, so he skipped the textbook and asked the vault instead, and it answered in his own words from 3 semesters back. Now the agent runs nightly, pulling 40 new notes a week writing summaries, tagging, linking, killing duplicates while he hasn't typed a note in 5 weeks. He opens the graph most mornings and scrolls for something he doesn't recognize, and there's always something. Tuition runs $59,320 a year; the vault cost one afternoon of setup. He built a second brain, then stopped using the first one.show more

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN... AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them insteadshow more

A STANFORD GUY POINTED CLAUDE CODE AT 11,400 OBSIDIAN... NOTES AND FOUND 214 ARGUMENTS HE'D HAD WITH HIMSELF 7 years of notes, 340MB of markdown, and a graph view that looked like a brain but never once thought. Every Sunday he opened the vault and every Sunday he closed it again. The second brain was a landfill with good lighting. So he stopped reading it and let something else read it instead. 47 lines of config, one instruction: find every pair of notes written 2+ years apart that contradict each other. 19 minutes on a 2021 MacBook Air, then 214 pairs. He had changed his mind 214 times in 7 years and caught himself doing it zero times. Then came the one that stopped him a note from March 2019, 62 words, sitting in a folder called "misc," describing the exact product he'd spent the last 5 months and $18,000 building a research doc around. He solved it in 2019, filed it, and forgot it existed. The vault never failed him, it stored all of it perfectly, it just had no way to speak. Now a cron job wakes at 6 AM, reads 40 notes, and writes 1 paragraph: here's what you believed then, here's what you believe now, here's the gap. He hasn't opened the graph view since. He didn't need a second brain, he needed the first one to answer back.show more

KIMI K3 + OBSIDIAN + LOOP ENGINEERING = A... VAULT THAT RUNS ITSELF the core idea: the vault is the loop's state, not the chat window everything Kimi K3 knows lives in a .md file the loop: > capture - a thought lands in 00-inbox > context - K3 pulls links, tags, and neighbouring notes > draft - edits happen inside a git worktree, never the live vault > review - a critic agent checks the diff before anything ships > commit - appended to the vault, nothing gets rewritten the key insight: frontmatter fields like supports, contradicts, and supersedes are graph edges, not metadata - the note format is the write API start with a plain loop, it runs about 2-4x the cost of one direct call > only move to a full graph once state has to outlive the session, several agents need to coordinate, or you have to explain what changed - that jump can run 10-50x one review assistant climbed from 55% to 72% to 84% just by moving through these shapes in ordershow more

This is the one GitHub repo that everyone needs... to save. The CEO of Obsidian literally open-sourced his entire Claude Skills vault. It's his personal Obsidian vault template, and it's built to 10x your AI productivity. To get started: 1. Download the vault in the GitHub link below 2. Unzip the .zip file (Claude can help here) 3. Open Obsidian & create a new vault pointing to that folder →show more

HERMES AGENT HAS A SECOND BRAIN. 1,100+ KNOWLEDGE FILES.... AUTO-LINKED. SELF-IMPROVING. GROWING EVERY NIGHT. THIS IS THE OBSIDIAN GRAPH BEHIND IT. every dot = one knowledge file (markdown) every line = one wiki-link between files every color = one category (skills, notes, decisions, sources, entities) HOW IT BUILDS ITSELF: Hermes ships with a bundled LLM Wiki skill. based on Andrej Karpathy's pattern. unlike RAG (rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. when you feed the agent a source: → it reads the content → writes a structured markdown page → auto-links to every related existing page → flags contradictions with previous entries → updates all affected pages one source in. multiple connections created. the graph grows denser with every entry. WHAT FEEDS THE WIKI: → articles and URLs you find interesting → meeting transcripts → PDF documents and research papers → conversation history from Hermes sessions → Claude Code and Codex session history → Slack logs, email threads, saved notes → YouTube transcripts → raw text dropped into a _raw/ folder the obsidian-wiki package supports multi-agent ingest from Hermes, Claude Code, Codex, OpenClaw, Pi, Windsurf, and ChatGPT exports. install: pip install obsidian-wiki obsidian-wiki setup --vault ~/wiki AUTOMATE THE GROWTH: set cron jobs to feed the wiki overnight: "every day at 9am, check for new meetings. ingest transcripts into the wiki." "every week, check arXiv for new papers in [niche]. summarize and file into the wiki." "every day, ingest today's Hermes sessions into the wiki under session-history." month 1: 50 entries. scattered. month 3: 300+ entries. cross-referenced. month 6: 1,000+ entries. the agent surfaces patterns you never searched for. WHY OBSIDIAN: the wiki is plain markdown files. no database. no lock-in. open it in Obsidian for graph view: → nodes show knowledge density → links show how ideas connect → clusters reveal your strongest domains → orphan nodes reveal gaps Hermes writes from a VPS. Obsidian reads on your laptop. obsidian-headless syncs without a GUI. agent writes from the server, you browse on your device. FOUR MEMORY LAYERS: Layer 1: memory.md + user.md (~2,200 + 1,375 chars. short-term.) Layer 2: SQLite with FTS5 (full session transcripts. searchable.) Layer 3: external providers (Mem0, SuperMemory, Honcho. optional.) Layer 4: Obsidian wiki via LLM Wiki skill (unlimited. compounding. the long-term brain.) layers 1-3 handle memory. layer 4 handles knowledge. the graph in this post is layer 4. SETUP: set in Desktop app, Dashboard, or config.yaml: WIKI_PATH=~/wiki OBSIDIAN_VAULT_PATH=~/wiki first run: Hermes asks for your domain. answer with your niche. the skill builds SCHEMA.md with tag taxonomy. after that: "index this into my wiki: [URL or text]" the wiki grows. the graph densifies. the agent gets smarter because the knowledge base got smarter. full 15 levels breakdown in the article 👇show more

Obsidian became a neural network with 184,320 links and... now runs as the most powerful second brain ever built for $0. 12,480 notes in 1 vault, 0 folders, 0 tabs, and he hasn't opened Notion in 7 months. Every night at 2 AM Claude Code walks the vault, reads all 12,480 notes, embeds them, and hunts for the pairs that should be linked but never were. Last night it found 61 and he accepted all 61. That's the move nobody makes by hand, because 12,480 notes means 77 million possible pairs, and a human links maybe 4 a day while the agent links 61 while he sleeps. Capture takes 2 seconds, a voice memo lands as a note in 1.4, a clip becomes a linked node on its own friction is what kills a second brain so he deleted the friction. Recall latency sits at 38 milliseconds, which means the graph answers before he finishes doubting himself. 36 clusters formed without him, decay score holds at 0.03, and 97% of everything he ever wrote is still reachable, while most people's notes rot past 90% in a year and turn into a graveyard with good search. Yesterday it surfaced 9 forgotten notes, one of them 412 days old, and that one became a product he shipped 48 hours later. Plain .md files on a laptop, no cloud, no subscription, no company that can delete his brain on a Tuesday. The graph doesn't store what he knows. It stores what he'd never have connected alone.show more

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE OPUS 5 +... OBSIDIAN Andrej Karpathy (OpenAI co-founder) shared an architecture that turns Claude into a persistent second brain not just a basic chat window how it works: > point Claude Code at an Obsidian vault folder > drop articles, PDFs, or video transcripts into raw > Claude reads them, updates summaries, cross-references everything > the knowledge base compounds like interest, never resets on a new chat the setup: > install create a local vault folder > open it in Claude Code, paste Karpathy's wiki prompt > > let the agent build raw, wiki, and CLAUDE.md folders > drop any file into raw, tell it to ingest > ask questions, get compiled summaries back this skips rag overhead entirely. your vault stays organized on its own run ingest on a schedule and it's loop engineering: sense a new file, plan, write, verify, repeat how do you manage your local knowledge base?show more

ANTHROPIC'S LEAD ENGINEER ACCIDENTALLY LEAKED HIS PERSONAL OBSIDIAN VAULT.... INSIDE - NO CODE, NO PROMPTS. JUST A SCHEMATIC OF HIS OWN MIND, BUILT LIKE A NEURAL NETWORK 8,893 nodes. 4,729 links. A $10-a-month app opens Obsidian. 21 inputs, 10+ hidden layers, ReLU activation. First layer 64 neurons, then 37, then 22, all the way to the output. Thousands of connections firing in real time this isn't a concept diagram from a blog - it's a living brain that actually runs decisions inside the company. 9,000 documents, each its own knowledge space, all interconnected he makes around $2M a year for putting markdown files into the right folders. The company building the best AI in the world manages its internal knowledge with the same app a college freshman uses for lecture notes. hasn't written a single line of infrastructure for any of it. three years of discipline and one open Obsidian tab you're reading this on a device where you could open the same Obsidian tonight and start building your own vaultshow more

THIS GUY HAD 1,283 NOTES AND HIS SYSTEM WAS... DUMBER THAN A FOLDER that galaxy in the background is his Obsidian vault > looks incredible > does nothing dead notes, zero connections, zero value extracted from any of it > the fix isn't taking better notes > it's building a pipeline where Claude Opus 4.8 does the research, NotebookLM does the analysis, and every session feeds your vault automatically one command: > Claude Code searches YouTube for 10 relevant sources > passes them to NotebookLM - Google's servers do the heavy processing, not your tokens > NotebookLM runs full analysis, generates infographics, mindmaps, flashcards > everything lands as structured markdown in your Obsidian vault, linked and ready total time: 6 minutes > after a month the vault knows your thinking style. after a year it's a trained research assistant the $300K AI architects aren't taking better notes > they're building systems that compound 30-minute setup. full step-by-step in the article below 👇show more

this is f**king dangerous Most people treat Claude like... a search bar. The ones with a second brain treat it as an intelligence layer on everything they know. Here's the 15-minute setup: → Install Claude Code → Install Obsidian, create a vault → Open it in Claude Code, drop in the CLAUDE.md schema — that one file is the engine → Throw any source in, say "ingest this" Done. From then on, everything you know is queryable by the most capable AI on earth. Claude wires each source against your whole vault and surfaces connections you forgot you had. Build it tonight. full A–Z guide below.show more

AN ANTHROPIC LEAD ENGINEER ACCIDENTALLY LEAKED HIS PERSONAL OBSIDIAN.... INSIDE - NOT CODE OR PROMPTS, BUT A DIAGRAM OF HIS OWN BRAIN, ORGANIZED AS A NEURAL NETWORK 8,893 nodes. 4,729 connections. A $10/month app opens Obsidian. 21 inputs, ReLU on every layer. The first hidden layer has 26 neurons, followed by 33, then 24, and so on all the way to the output. Thousands of connections flash in real time this isn’t a conceptual diagram from a blog, but a living brain that powers decision-making within the company. 9,000 documents, each with its own semantic space, all interconnected it earns about $2m a year for sorting Markdown files into the right folders. The company that builds the world’s best AI maintains its internal knowledge base in the same app that a freshman uses for class notes three years of discipline and a single open Obsidian tab you’re reading this on a device where, tonight, you can open that same Obsidian and start building your own vaultshow more

I genuinely don't understand why everyone isn't using this... yet Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: stop using AI to write code, use it to build a second brain. You point Claude Code at a folder, drop in any source, an article, a transcript, a PDF, and Claude reads it, links it, and files it into a living wiki of everything you know. It compounds like interest, the more you feed it, the smarter it gets. Here's the whole thing: > Install Obsidian, create a vault, open it in Claude Code > Paste Karpathy's wiki idea file and tell Claude to build it > Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it > Drop any source into raw and say "ingest this" > Ask questions across everything, forever Five minutes to set up, and you never start from a blank chat again. Full step-by-step guide with Claude and Obsidian, link below. Bookmark thisshow more

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN... THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription.show more

late to the party but built a UI layer... on top of the wiki my OpenClaw🦞 agent writes and maintains, based on exactly what Andrej Karpathy describes here. obsidian vault underneath, react frontend on top: search, an interactive knowledge graph, topic browsing, article pages with tables of contents + neighborhood mini-graph and many more.show more