Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

A guy in China plugged an LLM into Karpathy method + Claude Code and built a second brain that remembers everything forever. Not a note app, not RAG just 3 folders on a laptop. Folder 1 holds raw sources: articles, journal entries, chat logs. The LLM reads them but...

61,964 Aufrufe • vor 2 Monaten •via X (Twitter)

18 Kommentare

Profilbild von Aragorn Meulendijks
Aragorn Meulendijksvor 2 Monaten

Obsidian was nice for a month. Then I hit all its limitations, and realised obsidian is competely irrelevant.

Profilbild von 0xSlyth
0xSlythvor 2 Monaten

this is the future no question

Profilbild von MEE6
MEE6vor 2 Monaten

As long as you know how to use it properly

Profilbild von KC
KCvor 2 Monaten

I CAN EXPLODE A TENNIS BALL USING ONLY MY MIND

Profilbild von Alan Powichrowski
Alan Powichrowskivor 2 Monaten

Too much orchestration and management, it’s still a part time job managing this. Don’t you feel there’s a lot of friction to the process?

Profilbild von Iron Mind
Iron Mindvor 2 Monaten

Wow, looks stunning

Profilbild von Jyoti
Jyotivor 2 Monaten

That's awesome! It sounds like a really smart way to organize information. I'm curious to see how it evolves.

Profilbild von Nathan Bradforth
Nathan Bradforthvor 2 Monaten

I see an infinite set of growing fractles

Profilbild von expemilly
expemillyvor 2 Monaten

I thought people usually use Obsidian to create a second brain

Profilbild von 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNBvor 2 Monaten

给脑子挂了个外挂硬盘,听着就很折腾

Profilbild von AI Mastery Guide
AI Mastery Guidevor 2 Monaten

The Memex comparison is spot on, this finally feels like that idea built with maintenance solved.

Profilbild von Pixel
Pixelvor 2 Monaten

Karpathy method is doing the retrieval. CLAUDE.md is doing the discipline. Most people building "second brains" only bother with one of the two.

Profilbild von Saman Ahmed
Saman Ahmedvor 2 Monaten

I've been thinking a lot about AI memory systems lately. My take is the boring maintenance part was always the hardest piece to solve.

Profilbild von Pearl AI
Pearl AIvor 2 Monaten

AI memory is getting seriously interesting.

Profilbild von Praeston
Praestonvor 2 Monaten

I have a solution to that! Equilibrium layer which contains translations of processess and models from various domains into an abstract definition of a core fundamental model. When asked for solution in any domain, it just needs to identify a solution for the fundamental process

Profilbild von FOMO3D Phoenix Official
FOMO3D Phoenix Officialvor 2 Monaten

This is definitely not a novel invention.

Profilbild von Antonio D. Marasco
Antonio D. Marascovor 2 Monaten

Running this exact setup (Claude Code + Obsidian) for months. You nailed the part most miss: contradiction-flagging. Raw capture is easy; the value is the compile pass that distills notes into linked pages + a weekly "what am I missing?" gap scan. Makes it think, not just store.

Profilbild von Aryaman Upmanyu
Aryaman Upmanyuvor 2 Monaten

shifting the heavy lifting of knowledge maintenance from the user to an automated local file system finally makes the dream of the memex practical

Ähnliche Videos

Obsidian + Claude Code is how Andrej Karpathy turns 15 years of notes into a brain that works while he sleeps. The method behind it costs $0 and takes 5 minutes a day and it outlived every productivity app since 2011. Every idea, link, and half-thought gets appended to the top of a single note, with no sorting, no folders, no tags. Once a week he scrolls through, and anything that still matters gets copied back to the top. Weak ideas sink. Strong ideas resurface 5, 10, 20 times and by the 20th pass your brain has already wired them into everything else you know. Repetition as a filter. That's the whole system. Now the 2026 upgrade almost nobody is running: Drop that note into an Obsidian vault and open the folder with Claude Code not the chat app, the terminal agent that reads files. 3 commands change everything: read my last 30 days of notes and find the 3 ideas I keep circling without acting on link every note mentioning this project into a CLAUDE.md of what I actually believe about it draft this week's post from the idea that resurfaced most Claude Code doesn't search your vault it walks it, follows the wikilinks, and hands you the patterns you were too close to see. Karpathy method filters the signal, Obsidian stores it, Claude Code compounds it. One is a habit, one is a folder, one is $20 a month together they're the closest thing to a second brain that thinks back. Most people collect notes for 10 years and never read them once. His notes read him.

Spike 1%

12,467 Aufrufe • vor 1 Monat

Obsidian just became the most dangerous folder on your computer, and Andrej Karpathy predicted it with 1 markdown file. His method is called append-and-review. He described it years ago and almost nobody listened: 1 single note, every thought appended to the top, reviewed on random scrolls. No tags, no folders, no Notion dashboards with 40 linked databases. The problem was always the same the note remembers, but it can't act. That changed the moment people pointed Claude Code at an Obsidian vault. Here's the setup that's quietly spreading: Part 1 — The vault becomes a database. Obsidian stores everything as plain markdown on your disk, which means Claude Code can read it like a codebase. You open a terminal inside the vault folder and your 2,000 notes turn into queryable memory. Part 2 — The CLAUDEmd file becomes the brain stem. One file at the root tells the agent who you are, what you're building, and how your notes are structured. From that point every session starts with full context instead of a blank chat window. Part 3 — Karpathy append log becomes fuel. You dump raw thoughts all day ideas, links, half-sentences. Then 1 command at night: review today's appends, extract action items, draft the 3 posts hiding in there, link them to existing notes. The messy log goes in, structured output comes out, and the vault rewrites itself while you sleep. Part 4 — Agents start living in your notes. People are running weekly reviews, content calendars, even market research as scheduled Claude Code runs over their vault. Your second brain stops being a graveyard of highlights and starts shipping. The honest math: setup takes about 90 minutes, the first week feels like overkill, and by day 30 you're sitting on a system where every note you've written in 5 years is working for you instead of rotting in a folder. Notion needed a server, a subscription and your data on someone else's machine. Obsidian needed a text file and now the text file has an employee.

Spike 1%

58,428 Aufrufe • vor 2 Monaten

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,549 Aufrufe • vor 3 Monaten

A GUY MAKING $100K/MONTH WITH AI JUST SHOWED HIS ENTIRE SETUP. IT'S ONE FOLDER OF NOTES AND NOTHING ELSE no framework. no $500 course. he opens his screen and it's just obsidian - a plain notes app - wired into claude here's what he did: -> he pulled claude's memory files out of their default folder and dumped them into one vault -> had claude rename and merge them: 107 messy files collapsed into 17 clean ones -> every folder gets one master note that links to all the others that last part is the whole trick the agent reads the master note, follows the links and by the time it's done it has read every file in the folder. one instruction, full context here's the part most people miss: everyone's trying to make the AI smarter. he made the AI's memory smaller fewer files, better organized, all linked. the agent isn't scanning hundreds of notes anymore - it walks a path you built that's why his agent actually finishes jobs instead of forgetting what it was doing halfway through then he goes one step further: at the end of every session, the agent writes its own daily note. what it did, when, indexed at the top so it can find it again in seconds so he never re-explains anything. the agent looks up what it already did now he types "create a campaign for this offer" and walks away. it reads the product notes, reads the process notes, and comes back with the campaign done you don't need any of the complicated agent tools people are selling you. you need structure and instructions save this. the people winning with AI aren't using better models. they're just the only ones who bothered to organize what it remembers

Paone

23,833 Aufrufe • vor 2 Monaten

I still don’t understand why everyone isn’t running one of these yet. mine has been compiling for six months and it already knows things I’ve forgotten I knew Andrej Karpathy published a folder structure in April 2026. 5,000 stars. 16 million views. engineers couldn’t stop sharing it. not a model, not a tool, a folder structure. the sentence that explains why: “RAG re-derives knowledge on every query. a compiled wiki derives it once and keeps it current” most people who try building one hit a wall around month three anyway. the notes pile up, the links exist, and then it just sits there. you’re still the one doing all the remembering here’s the sentence that explains that wall too: keeping fifty interlinked notes current, consistent, and cross-referenced is work no human sustains. so people stop maintaining it, and it turns into a graveyard of good intentions the fix isn’t discipline. it’s making the system do the maintenance instead of you here’s the gist drop any source into a folder called raw, untouched, ground truth Claude reads it once, writes a structured page into wiki, links it to everything already there, flags anything that contradicts what you already know one file called CLAUDE.md sits at the center holding who you are, so you stop re-explaining yourself every session ask it anything across everything you’ve ever fed it, and it answers from months of compiled understanding instead of starting from zero that loop is the whole system. Karpathy’s repo got 16 million views because engineers finally saw the difference written down: retrieval answers questions, compilation builds understanding five minutes to set up. you’ll never open an empty chat and re-explain your life again full build, every step, in the article. save it now

rvaniaaa

54,967 Aufrufe • vor 12 Tagen