Loading video...

Video Failed to Load

Go Home

Anthropic engineer just built a second brain that reads 3 files instead of 5,000, and cut the token bill 40% no orchestrator, no plugin, just a router file, an index, and code that scores before the model ever opens anything point claude at a flat folder of notes and...

leopardracer's profile picture

leopardracer

11,115 subscribers

37,304 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

iit's wild that this still isn't the default way people use AI. Andrew Ng, a co-founder of Google Brain, gave a talk that crossed 2 million views: stop feeding your AI a folder of notes, build it a graph it can actually think with. his point is simple, stop making your AI read the whole vault to answer one thing. give it a graph, a router that points, an index that scores, edges that link, and it walks straight to the answer. it compounds, cheaper and faster the more you add. here's the whole thing: > point Claude at your notes and have it write a tiny router, your CLAUDE.md > build an index, one line per note, so it always knows where an answer lives > keep each note to one idea, and link the ones that depend on each other > make retrieval run as code, so it scores and opens the right files before the model thinks > tell it to prove the graph beats a flat folder on speed and cost, then keep the index fresh on every write set it up once and your AI stops guessing. it already knows your world before you type a word. full 12-step guide below. bookmark this.
0:23

iit's wild that this still isn't the default way people use AI. Andrew Ng, a co-founder of Google Brain, gave a talk that crossed 2 million views: stop feeding your AI a folder of notes, build it a graph it can actually think with. his point is simple, stop making your AI read the whole vault to answer one thing. give it a graph, a router that points, an index that scores, edges that link, and it walks straight to the answer. it compounds, cheaper and faster the more you add. here's the whole thing: > point Claude at your notes and have it write a tiny router, your CLAUDE.md > build an index, one line per note, so it always knows where an answer lives > keep each note to one idea, and link the ones that depend on each other > make retrieval run as code, so it scores and opens the right files before the model thinks > tell it to prove the graph beats a flat folder on speed and cost, then keep the index fresh on every write set it up once and your AI stops guessing. it already knows your world before you type a word. full 12-step guide below. bookmark this.

KingWilliam

15,099 views • 2 months ago

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
9:56

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 views • 2 months ago

Obsidian + Claude Code turned a 4,300-note vault into a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.
0:55

Obsidian + Claude Code turned a 4,300-note vault into a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.

Spike 1%

18,223 views • 2 months ago

Most people use Claude Code like a chatbot, then wonder why it forgets everything by Tuesday. The ones quietly building $10K AI workflows give it a second brain instead, and it’s free. It’s called Obsidian. You download it, point it at one folder on your computer, and that folder becomes a vault. Every note inside it is now something Claude Code can read end to end. Open Claude in that folder and it’s connected, that simple. The trick isn’t the tool, it’s the map. 3 folders, that’s the whole system. Raw, you dump everything here. Notes, transcripts, screenshots, half thoughts, zero structure. Wiki, Claude reads the raw pile and writes clean Wikipedia style articles about it, structured, searchable, permanent. Output, when you want a deliverable, a PDF, a slide deck, a script, it pulls from the wiki and ships it. Most people skip the wiki layer and feed Claude a junk drawer of 400 files, then blame the model when the answers are garbage. The model isn’t the problem, your folder is. Give it a path it can follow and it finds anything in 1 second, give it chaos and it guesses. You don’t even have to design the structure yourself. Open the vault, tell Claude to build a file system that fits your work, and watch it organize your entire brain in one prompt. Free tool, 3 folders, a second brain that compounds while you sleep. The people falling behind are still copy pasting into a chat window.
1:57

Most people use Claude Code like a chatbot, then wonder why it forgets everything by Tuesday. The ones quietly building $10K AI workflows give it a second brain instead, and it’s free. It’s called Obsidian. You download it, point it at one folder on your computer, and that folder becomes a vault. Every note inside it is now something Claude Code can read end to end. Open Claude in that folder and it’s connected, that simple. The trick isn’t the tool, it’s the map. 3 folders, that’s the whole system. Raw, you dump everything here. Notes, transcripts, screenshots, half thoughts, zero structure. Wiki, Claude reads the raw pile and writes clean Wikipedia style articles about it, structured, searchable, permanent. Output, when you want a deliverable, a PDF, a slide deck, a script, it pulls from the wiki and ships it. Most people skip the wiki layer and feed Claude a junk drawer of 400 files, then blame the model when the answers are garbage. The model isn’t the problem, your folder is. Give it a path it can follow and it finds anything in 1 second, give it chaos and it guesses. You don’t even have to design the structure yourself. Open the vault, tell Claude to build a file system that fits your work, and watch it organize your entire brain in one prompt. Free tool, 3 folders, a second brain that compounds while you sleep. The people falling behind are still copy pasting into a chat window.

West Lord

32,845 views • 3 months ago

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.
1:29

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 views • 2 months ago

The "Karpathy Method" Obsidian + Claude Code is quietly replacing $15/month note apps for 1000s of builders. The setup costs $0. Takes 10 minutes. And it's stupidly simple. Karpathy stores his entire brain in plain markdown files. No Notion. No database. A folder. People mocked it for years. Then Claude Code shipped an agent that lives in the terminal and reads files natively. Obsidian IS files. Notion hides your notes behind an API. Obsidian hands them to the agent raw. The "boomer stack" turned out to be the only one AI can walk through end to end. The method, 4 steps: Open your vault folder in terminal. Type claude. The agent now sees 100% of your notes. Drop a CLAUDE.md at the root. 40 lines: how you tag, how you link, what a good note looks like. Your brain's operating manual. Run 1 nightly job. Claude reads the day's dump links, highlights, half-thoughts and files it into atomic notes with backlinks. Once a week, ask 1 question: "what connects that I haven't connected?" Old notes collide into ideas you'd never find alone. A builder running this loop hit 4,120 notes in 5 months. Found 2 essay ideas in the collisions. Sold both for $3,400. Hardware: a $599 Mac Mini. Software: a folder. The industry spent 10 years building smarter note apps. Karpathy bet on the file. The file won.
0:30

The "Karpathy Method" Obsidian + Claude Code is quietly replacing $15/month note apps for 1000s of builders. The setup costs $0. Takes 10 minutes. And it's stupidly simple. Karpathy stores his entire brain in plain markdown files. No Notion. No database. A folder. People mocked it for years. Then Claude Code shipped an agent that lives in the terminal and reads files natively. Obsidian IS files. Notion hides your notes behind an API. Obsidian hands them to the agent raw. The "boomer stack" turned out to be the only one AI can walk through end to end. The method, 4 steps: Open your vault folder in terminal. Type claude. The agent now sees 100% of your notes. Drop a CLAUDE.md at the root. 40 lines: how you tag, how you link, what a good note looks like. Your brain's operating manual. Run 1 nightly job. Claude reads the day's dump links, highlights, half-thoughts and files it into atomic notes with backlinks. Once a week, ask 1 question: "what connects that I haven't connected?" Old notes collide into ideas you'd never find alone. A builder running this loop hit 4,120 notes in 5 months. Found 2 essay ideas in the collisions. Sold both for $3,400. Hardware: a $599 Mac Mini. Software: a folder. The industry spent 10 years building smarter note apps. Karpathy bet on the file. The file won.

Selina

36,122 views • 2 months ago

this model runs coding agents for $0.30 per million tokens and someone just wired it into an entire company most people arguing about AI agents online have never watched one actually run a business types → seeded world → store → heartbeat → memory → cockpit → gate → command line → runtime nine files, one shared state, every screen just reads from it, nobody’s faking their own copy fail a policy check and the approve button turns into “override” instead, so nobody clicks past a red flag by accident that gate is the only reason an agent gets to touch money without someone standing over it bookmark this and watch it run, then read the article below
0:22

this model runs coding agents for $0.30 per million tokens and someone just wired it into an entire company most people arguing about AI agents online have never watched one actually run a business types → seeded world → store → heartbeat → memory → cockpit → gate → command line → runtime nine files, one shared state, every screen just reads from it, nobody’s faking their own copy fail a policy check and the approve button turns into “override” instead, so nobody clicks past a red flag by accident that gate is the only reason an agent gets to touch money without someone standing over it bookmark this and watch it run, then read the article below

leopardracer

28,047 views • 2 months ago

"how do you remember everything you read?" I don't. Claude does. every article, PDF, and transcript goes into one Obsidian folder. Claude reads it, breaks it into atomic notes, links it to the rest. I just ask. that's Karpathy's second-brain method. three folders, one file. full guide below.
0:25

"how do you remember everything you read?" I don't. Claude does. every article, PDF, and transcript goes into one Obsidian folder. Claude reads it, breaks it into atomic notes, links it to the rest. I just ask. that's Karpathy's second-brain method. three folders, one file. full guide below.

Kirill

88,119 views • 2 months ago

Andrej Karpathy quietly shipped the best second brain idea in years not an app. a pattern. let an llm maintain a wiki of your notes. you dump sources, it reads them, links them, files them. knowledge compounds like interest. someone built it into a free claude code plugin. setup is two commands: claude plugin marketplace add AgriciDaniel/claude-obsidian claude plugin install claude-obsidian@agricidaniel-claude-obsidian then open obsidian, open claude code in the same folder, type /wiki. that's it. your notes are now queryable by claude and they get richer every time you read something. bookmark this. best thing you'll build this weekend.
0:42

Andrej Karpathy quietly shipped the best second brain idea in years not an app. a pattern. let an llm maintain a wiki of your notes. you dump sources, it reads them, links them, files them. knowledge compounds like interest. someone built it into a free claude code plugin. setup is two commands: claude plugin marketplace add AgriciDaniel/claude-obsidian claude plugin install claude-obsidian@agricidaniel-claude-obsidian then open obsidian, open claude code in the same folder, type /wiki. that's it. your notes are now queryable by claude and they get richer every time you read something. bookmark this. best thing you'll build this weekend.

Avid

339,134 views • 3 months ago

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit
27:26

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

NO1ennn

13,015 views • 2 months ago

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this
13:23

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,559 views • 4 months ago

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 never touches them. Folder 2 is the wiki hundreds of markdown pages the LLM writes and maintains itself, where every person, idea and decision gets filed, cross-referenced and kept current. Folder 3 is one file: CLAUDEmd, the rulebook that turns a chatbot into a librarian. He drops in a new article and Claude reads it, updates 10-15 pages, flags what contradicts his old notes, logs the timestamp while he watches his memory grow node by node in Obsidian graph view. Ask it anything and it doesn’t dig through raw files like ChatGPT does the synthesis already exists, the connections are already drawn. The method comes from a gist Karpathy posted on April 4, now sitting at 5,000 stars and 5,000 forks, with 1 production team already scaled to 4,000 interlinked concepts in 6 months. The part nobody mentions: Vannevar Bush described this exact machine in 1945 the Memex, a personal memory store with trails between documents. Nobody built it for 81 years because someone had to do the maintenance. Now maintenance costs nothing the LLM does the filing while the human does the thinking. Every article makes the brain smarter, and it never forgets. His memory has a git history now.
0:28

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 never touches them. Folder 2 is the wiki hundreds of markdown pages the LLM writes and maintains itself, where every person, idea and decision gets filed, cross-referenced and kept current. Folder 3 is one file: CLAUDEmd, the rulebook that turns a chatbot into a librarian. He drops in a new article and Claude reads it, updates 10-15 pages, flags what contradicts his old notes, logs the timestamp while he watches his memory grow node by node in Obsidian graph view. Ask it anything and it doesn’t dig through raw files like ChatGPT does the synthesis already exists, the connections are already drawn. The method comes from a gist Karpathy posted on April 4, now sitting at 5,000 stars and 5,000 forks, with 1 production team already scaled to 4,000 interlinked concepts in 6 months. The part nobody mentions: Vannevar Bush described this exact machine in 1945 the Memex, a personal memory store with trails between documents. Nobody built it for 81 years because someone had to do the maintenance. Now maintenance costs nothing the LLM does the filing while the human does the thinking. Every article makes the brain smarter, and it never forgets. His memory has a git history now.

West Lord

62,105 views • 2 months ago

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this
16:36

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

Yarchi

141,580 views • 3 months ago

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓
0:47

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

44,226 views • 25 days ago

ANTHROPIC JUST KILLED A DOZEN AI MEMORY STARTUPS WITH ONE BUILT IN TOOL people raised millions to give AI long term memory. Anthropic just shipped it straight into the API. free, no framework, no vector database. it is a folder of files Claude reads and writes. that is it. the trick: it is client side. Claude never touches your data directly. it only requests a file operation, and your app runs it against storage you control. before every task Claude checks its /memories directory, pulls back what it learned last time, and keeps going. when it learns something new, it writes it down. six plain operations do all of it: > view, create, str_replace, insert, delete, rename why it actually wins: > just in time retrieval, it reads on demand instead of loading everything up front > it survives a context reset, so a long job resumes instead of starting over > every path is locked to /memories, so it cannot wander your filesystem > works on every Claude 4 model, no beta flag, generally available Anthropic even pairs it with context editing and compaction, so the live window stays tiny while the important stuff lives on disk. the whole thing in one line: Claude keeps the notes, you keep the storage. bookmark this before you pay for a memory layer you no longer need.
0:26

ANTHROPIC JUST KILLED A DOZEN AI MEMORY STARTUPS WITH ONE BUILT IN TOOL people raised millions to give AI long term memory. Anthropic just shipped it straight into the API. free, no framework, no vector database. it is a folder of files Claude reads and writes. that is it. the trick: it is client side. Claude never touches your data directly. it only requests a file operation, and your app runs it against storage you control. before every task Claude checks its /memories directory, pulls back what it learned last time, and keeps going. when it learns something new, it writes it down. six plain operations do all of it: > view, create, str_replace, insert, delete, rename why it actually wins: > just in time retrieval, it reads on demand instead of loading everything up front > it survives a context reset, so a long job resumes instead of starting over > every path is locked to /memories, so it cannot wander your filesystem > works on every Claude 4 model, no beta flag, generally available Anthropic even pairs it with context editing and compaction, so the live window stays tiny while the important stuff lives on disk. the whole thing in one line: Claude keeps the notes, you keep the storage. bookmark this before you pay for a memory layer you no longer need.

NO1ennn

42,946 views • 1 month ago

🚨 THIS 100% FREE GITHUB REPO JUST MADE EVERY AI NOTE-TAKING APP POINTLESS. Drop any source in article, PDF, YouTube transcript, or Journal entry. Claude reads it, links it to everything in your vault, and files it into a connected knowledge graph on your own machine. Most tools save your notes. This one connects them. Every source gets linked to everything you already know. Karpathy described the idea - 15 skills. Four vault methods. Works with Claude Code, Codex, and Gemini. Most people have years of knowledge buried in folders they open twice a year. This turns all of it into a second brain that works while you sleep. MY ARTICLE COVERS THE EXACT METHOD I BUILT TO DO THE SAME THING. Guide below!
0:23

🚨 THIS 100% FREE GITHUB REPO JUST MADE EVERY AI NOTE-TAKING APP POINTLESS. Drop any source in article, PDF, YouTube transcript, or Journal entry. Claude reads it, links it to everything in your vault, and files it into a connected knowledge graph on your own machine. Most tools save your notes. This one connects them. Every source gets linked to everything you already know. Karpathy described the idea - 15 skills. Four vault methods. Works with Claude Code, Codex, and Gemini. Most people have years of knowledge buried in folders they open twice a year. This turns all of it into a second brain that works while you sleep. MY ARTICLE COVERS THE EXACT METHOD I BUILT TO DO THE SAME THING. Guide below!

Kanika

38,795 views • 2 months ago

MOST "SECOND BRAINS" ARE JUST FOLDERS YOU FEEL GUILTY ABOUT. HERE'S HOW CLAUDE TURNS ONE INTO A BRAIN THAT ANSWERS YOU. that clip is the build: obsidian plus claude, structured like a filing cabinet. three drawers, one job each: raw: everything you dump in, docs, sheets, pdfs, transcripts, untouched new knowledge: what claude distills, links and rewrites into clean notes and the connections between them, drawn automatically the part most note apps miss: you are not the librarian. you drop the raw in. claude reads it once, files it, links it to what you already had, and updates the index. then you never dig through the raw pile again. you ask the brain, and it answers from the clean layer with sources. that graph on screen isn't decoration. every line is a connection you didn't have to make by hand. no re-reading the same pdf, no notes you wrote once and never opened, no app that guilts you for not organizing. the uncomfortable part isn't that note apps are messy. it's that a second brain was never about saving more, it was about something rereading you after you stopped. follow RetroChainer for systems that keep thinking after you close the tab, and bookmark this before your notes turn into another graveyard.
1:25

MOST "SECOND BRAINS" ARE JUST FOLDERS YOU FEEL GUILTY ABOUT. HERE'S HOW CLAUDE TURNS ONE INTO A BRAIN THAT ANSWERS YOU. that clip is the build: obsidian plus claude, structured like a filing cabinet. three drawers, one job each: raw: everything you dump in, docs, sheets, pdfs, transcripts, untouched new knowledge: what claude distills, links and rewrites into clean notes and the connections between them, drawn automatically the part most note apps miss: you are not the librarian. you drop the raw in. claude reads it once, files it, links it to what you already had, and updates the index. then you never dig through the raw pile again. you ask the brain, and it answers from the clean layer with sources. that graph on screen isn't decoration. every line is a connection you didn't have to make by hand. no re-reading the same pdf, no notes you wrote once and never opened, no app that guilts you for not organizing. the uncomfortable part isn't that note apps are messy. it's that a second brain was never about saving more, it was about something rereading you after you stopped. follow RetroChainer for systems that keep thinking after you close the tab, and bookmark this before your notes turn into another graveyard.

RetroChainer

13,775 views • 2 months ago

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.
0:50

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

NO1ennn

13,359 views • 2 months ago

STOP TREATING YOUR OBSIDIAN VAULT AS AI MEMORY. WITHOUT ONE ROUTING FILE, CLAUDE IS BURNING TOKENS ON NOISE YOU FORGOT YOU SAVED. a folder full of markdown does not make Claude smart. what makes it smart is what your agent can find without rereading the whole vault. storage: write → tag → graph → agent scans everything the model touches the entire vault, hallucinates half of it, forgets by the next session. memory: write → index → route → agent opens two files the model reads the index first, follows one path, answers with a link back to the note. i have rebuilt my Obsidian vault three times this year. the first two collapsed inside a month because Claude kept guessing which folder to open. the third one holds because the first thing i ship now is the routing file. Markdown, links, and the graph view are not what changed. what changed was a one-line description per folder, written for the agent, kept current, loaded before any retrieval call. if your agent still starts every session by scanning your whole vault, you are running storage. write the routing file today.
0:20

STOP TREATING YOUR OBSIDIAN VAULT AS AI MEMORY. WITHOUT ONE ROUTING FILE, CLAUDE IS BURNING TOKENS ON NOISE YOU FORGOT YOU SAVED. a folder full of markdown does not make Claude smart. what makes it smart is what your agent can find without rereading the whole vault. storage: write → tag → graph → agent scans everything the model touches the entire vault, hallucinates half of it, forgets by the next session. memory: write → index → route → agent opens two files the model reads the index first, follows one path, answers with a link back to the note. i have rebuilt my Obsidian vault three times this year. the first two collapsed inside a month because Claude kept guessing which folder to open. the third one holds because the first thing i ship now is the routing file. Markdown, links, and the graph view are not what changed. what changed was a one-line description per folder, written for the agent, kept current, loaded before any retrieval call. if your agent still starts every session by scanning your whole vault, you are running storage. write the routing file today.

kocer

17,240 views • 1 month ago

Fable 5 and Karpathy's knowledge base trick are basically a cheat code. Someone just dropped a full walkthrough on building the most powerful second brain ever Andrej Karpathy shared a simple idea: use an LLM to build personal knowledge bases. Index your sources, let the model organize them, and use Obsidian as the front end. Someone just built the full thing with Claude Code and Fable 5, and walked through every step You drop your sources into a folder (YouTube transcripts, PDFs, articles, meeting notes) and Claude Code reads them, splits them into linked wiki pages, and builds a living second brain that connects everything. It grows on its own as you add more. Where Fable 5 pulls ahead: it found a connection buried across two sources you'd miss reading them separately. And asked to turn the messy web of links into something a beginner could understand, it produced clean, simple HTML in one shot. The same task took a full day on Opus 4.8 and came out worse. The best part: it's all just markdown files with routing. So it's not locked to Claude Code. Plug it into Codex or any agent you want. Give your AI a real knowledge base, and it stops guessing and starts knowing. Bookmark this.
14:34

Fable 5 and Karpathy's knowledge base trick are basically a cheat code. Someone just dropped a full walkthrough on building the most powerful second brain ever Andrej Karpathy shared a simple idea: use an LLM to build personal knowledge bases. Index your sources, let the model organize them, and use Obsidian as the front end. Someone just built the full thing with Claude Code and Fable 5, and walked through every step You drop your sources into a folder (YouTube transcripts, PDFs, articles, meeting notes) and Claude Code reads them, splits them into linked wiki pages, and builds a living second brain that connects everything. It grows on its own as you add more. Where Fable 5 pulls ahead: it found a connection buried across two sources you'd miss reading them separately. And asked to turn the messy web of links into something a beginner could understand, it produced clean, simple HTML in one shot. The same task took a full day on Opus 4.8 and came out worse. The best part: it's all just markdown files with routing. So it's not locked to Claude Code. Plug it into Codex or any agent you want. Give your AI a real knowledge base, and it stops guessing and starts knowing. Bookmark this.

Shadow Nick

47,331 views • 3 months ago