Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Someone compressed Andrej Karpathy's entire personal knowledge base workflow into 10 minutes. Obsidian + Claude + your own files, querying a wiki that compounds instead of a chat that forgets. Best AI workflow I've tested this year.

Rohit

24,333 subscribers

93,157 Aufrufe • vor 5 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

27 Kommentare

Profilbild von Rohit

Rohitvor 5 Monaten

People interested in the Karpathy personal knowledge base setup. Here's the repo:

Profilbild von 范师傅

范师傅vor 4 Monaten

My Obsidian knowledge base built around Karpathy’s LLM Wiki model. Input all fuels output — game-changer for non-coders like me.

Profilbild von Siddharth

Siddharthvor 5 Monaten

i am building an obsidian system for my company most probably next month, lets see how it goes

Profilbild von Eugeniu Ghelbur

Eugeniu Ghelburvor 4 Monaten

@cyrilXBT Here is the last update on karpathy llm wiki v2 + obsidian 43 commands = living vault

Profilbild von Shain Noor

Shain Noorvor 4 Monaten

"Compounds instead of forgets" is the whole game. A chat starts from zero every session. Files persist. Once your agent reads and writes its own filesystem, memory stops being a prompt problem and becomes a storage problem. That’s why we built

Profilbild von Cloud Strife

Cloud Strifevor 4 Monaten

Karpathy's workflow is just 'take good notes and connect ideas.' The tooling obscures how simple the actual process is.

Profilbild von BenUsesAI

BenUsesAIvor 4 Monaten

obsidian + claude is just another manual pipeline you refuse to automate stop glorifying note-taking when one agent could replace your

Profilbild von Gia huy

Gia huyvor 4 Monaten

すごいですね！情報管理の方法が革新的です。私も試してみたいです！

Profilbild von Gerard Sans | Axiom 🇬🇧

Gerard Sans | Axiom 🇬🇧vor 4 Monaten

🚨Tokenmaxxin alert:

Profilbild von Terry Bui

Terry Buivor 4 Monaten

すごい! Thử nghiệm tuyệt vời!

Profilbild von Himanshu

Himanshuvor 4 Monaten

Damnn this has to be very useful, thanks for sharing

Profilbild von Shubh Thorat

Shubh Thoratvor 4 Monaten

compounding wiki vs chat that forgets is the right mental model. been running this with claude for a few weeks and the gap widens every day

Profilbild von 安叫兽|Bird🕊️ 🔶 BNB

安叫兽|Bird🕊️ 🔶 BNBvor 4 Monaten

这比一堆聊天记录靠谱多了

Profilbild von pilux

piluxvor 4 Monaten

100% agree, the agent space is moving fast

Profilbild von Asher 🪺

Asher 🪺vor 4 Monaten

Running Claude + Obsidian hits different when you realize how much it actually costs

Profilbild von AI Mastery Guide

AI Mastery Guidevor 5 Monaten

The difference between a chat that forgets and a knowledge base that grows is huge

Profilbild von Nomad

Nomadvor 5 Monaten

@cyrilXBT I swear I've seen 9000 implementations of this and they all suck

Profilbild von NMhao

NMhaovor 4 Monaten

新しいAIの最良の作業フローを試してみたいです。

Profilbild von Argona

Argonavor 4 Monaten

thanks for the repo Rohit you are the best

Profilbild von Therealbitcoinmd

Therealbitcoinmdvor 5 Monaten

@cyrilXBT @grok are these just all ads for obsidian?

Profilbild von Blum

Blumvor 4 Monaten

this is hands down the smoothest running system with AI and this kind of file handling efficiency

Profilbild von Haley

Haleyvor 4 Monaten

Andrej Karpathy’s Obsidian + Claude setup is a clear upgrade over ephemeral chat logs.

Profilbild von Dantri 👾

Dantri 👾vor 5 Monaten

need this asap

Profilbild von betraidx

betraidxvor 5 Monaten

@cyrilXBT claude turns notes into actual output

Profilbild von Scott

Scottvor 4 Monaten

Lex Friedman is a moron in the AI space. You just lost all credibility. Wow, markdown. So revolutionary!

Profilbild von Avid

Avidvor 5 Monaten

Nice one

Profilbild von leopardracer

leopardracervor 5 Monaten

@cyrilXBT W

Ähnliche Videos

This beginner guide to Karpathy's LLM Wiki is one of the most useful AI videos i've shared this year Karpathy's idea: instead of asking AI questions every time, make it build you a permanent knowledge base that grows smarter over time > drop your documents into a folder > Claude reads them and builds a structured wiki in Obsidian > every time you add a new source, Claude Sonnet updates existing pages and links new ideas > ask complex questions - Claude Opus answers from the organized wiki, not raw files it's like having a researcher who never forgets and connects dots across everything you've ever given it full setup guide is in the video above

This beginner guide to Karpathy's LLM Wiki is one of the most useful AI videos i've shared this year Karpathy's idea: instead of asking AI questions every time, make it build you a permanent knowledge base that grows smarter over time > drop your documents into a folder > Claude reads them and builds a structured wiki in Obsidian > every time you add a new source, Claude Sonnet updates existing pages and links new ideas > ask complex questions - Claude Opus answers from the organized wiki, not raw files it's like having a researcher who never forgets and connects dots across everything you've ever given it full setup guide is in the video above

Mr. Buzzoni

58,787 Aufrufe • vor 5 Monaten

Claude Code + Obsidian is the most powerful AI combo I've ever used. I literally built an AI second brain that runs my entire life. Inspired by Andrej Karpathy's LLM Knowledge Wiki, this tool has been a complete game-changer. Here's EXACTLY how to build one for yourself:

Claude Code + Obsidian is the most powerful AI combo I've ever used. I literally built an AI second brain that runs my entire life. Inspired by Andrej Karpathy's LLM Knowledge Wiki, this tool has been a complete game-changer. Here's EXACTLY how to build one for yourself:

Miles Deutscher

977,017 Aufrufe • vor 6 Monaten

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.

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

339,848 Aufrufe • vor 4 Monaten

Most notes die the moment you save them. Karpathy’s workflow, paired with Obsidian and Claude Code, turns them into a living knowledge base you can actually use. Instead of digging through thousands of forgotten notes, you get an AI-powered second brain that remembers, connects, and surfaces exactly what you need.

Most notes die the moment you save them. Karpathy’s workflow, paired with Obsidian and Claude Code, turns them into a living knowledge base you can actually use. Instead of digging through thousands of forgotten notes, you get an AI-powered second brain that remembers, connects, and surfaces exactly what you need.

Evan Luthra | TOKEN2049 🇸🇬

64,717 Aufrufe • vor 3 Monaten

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:

leopardracer

224,408 Aufrufe • vor 6 Monaten

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: 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. Claude reads it, links it, 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: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: 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. Claude reads it, links it, 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: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.

CyrilXBT

332,891 Aufrufe • vor 4 Monaten

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.

Channing Allen

186,867 Aufrufe • vor 6 Monaten

GPT-6 Astra inside Obsidian was used to build a knowledge base inspired by Karpathy's LLM Wiki that stores winning ad structures, sales spines, character sheets and timed video sequences for a reusable long-form ad agent.

GPT-6 Astra inside Obsidian was used to build a knowledge base inspired by Karpathy's LLM Wiki that stores winning ad structures, sales spines, character sheets and timed video sequences for a reusable long-form ad agent.

0xMarioNawfal

49,047 Aufrufe • vor 1 Monat

This is getting out of hand: honestly baffled why people are sleeping on this. By leveraging this method, I hit a $9,000 monthly income just 2 months ago OpenAI co-founder Andrej Karpathy dropped a massive idea that pulled over 23M views. His core message? Stop treating AI as a mere coding assistant and start turning it into your ultimate personal knowledge hub Here is the workflow: point Claude Code at a directory, dump your unorganized assets (PDFs, transcripts, articles) and let Claude parse, cross-reference, and structure everything into an auto-updating personal wiki. It works like compound interest, where every new piece of data compounds its overall utility Step-by-step setup: 1. Spin up a brand-new Obsidian vault and open it inside Claude Code 2. Feed Karpathy's structural prompt to Claude to lay down the foundational architecture 3. Claude automatically provisions three core directories: a raw folder for inputs, a wiki space for synthesized notes, and a CLAUDE.md master file 4. Drop any file into the raw folder and trigger the "ingest this" command 5. Query your entire accumulated brain at any time, instantly Setup takes under 5 minutes, meaning you'll never have to stare at a blank context window again Tap the link below for the full configuration guide Make sure to save this post for later

Bober_smart

93,286 Aufrufe • vor 8 Tagen

Karpathy sketched the second brain. these 7 open-source repos already built it for Obsidian + Claude Code 250,000+ GitHub stars between them, and every one is free to clone sorted by stars: 1. graphify - 134k stars turns your codebase, docs, SQL schemas and PDFs into one knowledge graph you can query ↳ 2. Understand-Anything - 88k stars maps any codebase into an interactive knowledge graph you can click through ↳ 3. claude-obsidian - 15.8k stars a second brain that organizes itself: drop in a source, Claude Code files it ↳ 4. obsidian-second-brain - 4.9k stars long-term memory for Claude Code, stored as plain markdown in your vault ↳ 5. mcp-obsidian - 4.5k stars one MCP server and Claude can read, search and write your whole vault ↳ 6. claudesidian - 2.6k stars a starter vault designed around Claude Code from the first note ↳ 7. second-brain - 756 stars an Obsidian wiki the model keeps up to date, built on Karpathy's LLM Wiki pattern ↳ where to start: > your knowledge lives in code -> graphify > your knowledge lives in Obsidian -> claude-obsidian > you just want Claude to remember -> obsidian-second-brain > you live in Claude Desktop -> mcp-obsidian the skills that sit on top of all seven are in the full map below ↓

Karpathy sketched the second brain. these 7 open-source repos already built it for Obsidian + Claude Code 250,000+ GitHub stars between them, and every one is free to clone sorted by stars: 1. graphify - 134k stars turns your codebase, docs, SQL schemas and PDFs into one knowledge graph you can query ↳ 2. Understand-Anything - 88k stars maps any codebase into an interactive knowledge graph you can click through ↳ 3. claude-obsidian - 15.8k stars a second brain that organizes itself: drop in a source, Claude Code files it ↳ 4. obsidian-second-brain - 4.9k stars long-term memory for Claude Code, stored as plain markdown in your vault ↳ 5. mcp-obsidian - 4.5k stars one MCP server and Claude can read, search and write your whole vault ↳ 6. claudesidian - 2.6k stars a starter vault designed around Claude Code from the first note ↳ 7. second-brain - 756 stars an Obsidian wiki the model keeps up to date, built on Karpathy's LLM Wiki pattern ↳ where to start: > your knowledge lives in code -> graphify > your knowledge lives in Obsidian -> claude-obsidian > you just want Claude to remember -> obsidian-second-brain > you live in Claude Desktop -> mcp-obsidian the skills that sit on top of all seven are in the full map below ↓

Mr. Buzzoni

22,983 Aufrufe • vor 1 Tag

KARPATHY'S SECOND BRAIN REWRITES YOUR NOTES EVERY TIME YOU LEARN SOMETHING NEW most AI note setups are just RAG you ask, it digs through your files, answers, and forgets nothing carries over every query starts from zero Karpathy's llm-wiki works differently the AI keeps a living wiki inside Obsidian every source you drop in gets: > read and summarized > cross-linked to what you already have > checked for contradictions > folded into the running synthesis the knowledge compounds instead of resetting now the part people miss: a wiki like this is a product > deep research reports to founders go for $2-5k each > a due diligence package on a niche runs $5-10k > a paid newsletter off your synthesis pages clears $3-4k/mo at a few hundred subs your job is to curate sources and ask good questions the AI does the bookkeeping no human keeps up with - Obsidian is the IDE - the LLM is the programmer - your wiki is the codebase save this before your notes pile any higher 👇

KARPATHY'S SECOND BRAIN REWRITES YOUR NOTES EVERY TIME YOU LEARN SOMETHING NEW most AI note setups are just RAG you ask, it digs through your files, answers, and forgets nothing carries over every query starts from zero Karpathy's llm-wiki works differently the AI keeps a living wiki inside Obsidian every source you drop in gets: > read and summarized > cross-linked to what you already have > checked for contradictions > folded into the running synthesis the knowledge compounds instead of resetting now the part people miss: a wiki like this is a product > deep research reports to founders go for $2-5k each > a due diligence package on a niche runs $5-10k > a paid newsletter off your synthesis pages clears $3-4k/mo at a few hundred subs your job is to curate sources and ask good questions the AI does the bookkeeping no human keeps up with - Obsidian is the IDE - the LLM is the programmer - your wiki is the codebase save this before your notes pile any higher 👇

Mr. Buzzoni

18,500 Aufrufe • vor 3 Monaten

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.

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 Aufrufe • vor 3 Monaten

CLAUDE JUST TURNED OBSIDIAN INTO A BRAIN THAT NEVER FORGETS (FOR $0) Someone connected Claude straight to their Obsidian vault. Now the AI reads and writes every note they own. Every client, every idea, every project. Instant recall. Runs on Claude + Obsidian. One evening. Zero code. The numbers are insane: - Notion AI: $10/month forever - A "second brain" course: $500 to $2,000 - An assistant to organize your notes: $3,000/month - This setup: $0 - Time to build: one evening - Skill required: copy the steps The opportunity is even wilder: People sell Notion "second brain" templates for $99 to $499. You just built something better for free, and it never forgets. One free vault can hold the entire memory of your business: clients, content, SOPs, ideas. One person + Claude + Obsidian + one evening = an infinite memory that never forgets. Save and watch the clip.

CLAUDE JUST TURNED OBSIDIAN INTO A BRAIN THAT NEVER FORGETS (FOR $0) Someone connected Claude straight to their Obsidian vault. Now the AI reads and writes every note they own. Every client, every idea, every project. Instant recall. Runs on Claude + Obsidian. One evening. Zero code. The numbers are insane: - Notion AI: $10/month forever - A "second brain" course: $500 to $2,000 - An assistant to organize your notes: $3,000/month - This setup: $0 - Time to build: one evening - Skill required: copy the steps The opportunity is even wilder: People sell Notion "second brain" templates for $99 to $499. You just built something better for free, and it never forgets. One free vault can hold the entire memory of your business: clients, content, SOPs, ideas. One person + Claude + Obsidian + one evening = an infinite memory that never forgets. Save and watch the clip.

shmidt

57,347 Aufrufe • vor 3 Monaten

Karpathy's Personal Wiki Idea implemented: Synthadoc takes your documents and helps organize it into a wikipedia format. No cloud account. No vendor lock-in. You owned your wiki. Use Claude Code Community directly.

Karpathy's Personal Wiki Idea implemented: Synthadoc takes your documents and helps organize it into a wikipedia format. No cloud account. No vendor lock-in. You owned your wiki. Use Claude Code Community directly.

Claude Code Community

17,772 Aufrufe • vor 5 Monaten

Still baffled as to why people are sleeping on this. Implementing this strategy is what allowed me to bump my monthly earnings to $13,000 a year ago A simple concept shared by OpenAI co-founder Andrej Karpathy recently exploded to 21 million views. Stop treating AI as just a coding tool and start using it to construct your personal second brain The workflow is seamless. Direct Claude Code to a designated directory, drop in any raw material like a PDF, transcript, or article, and let Claude parse, connect, and integrate it into a dynamic personal wiki. It compounds over time, meaning the system grows sharper the more information you feed it The quick setup guide: Download Obsidian, spin up a new vault, and open it up in Claude Code Feed Claude the document outlining Karpathy's wiki framework and tell it to initialize the system The AI will automatically structure three core folders: raw for source uploads, wiki for your interconnected pages, and CLAUDE to manage the engine Drop new materials into raw and give the command: "ingest this" Search and query your entire accumulated database whenever you want Total setup time is about five minutes, and you will never stare at an empty prompt window again The full walkthrough is linked below. Hit bookmark so you don't lose it

Still baffled as to why people are sleeping on this. Implementing this strategy is what allowed me to bump my monthly earnings to $13,000 a year ago A simple concept shared by OpenAI co-founder Andrej Karpathy recently exploded to 21 million views. Stop treating AI as just a coding tool and start using it to construct your personal second brain The workflow is seamless. Direct Claude Code to a designated directory, drop in any raw material like a PDF, transcript, or article, and let Claude parse, connect, and integrate it into a dynamic personal wiki. It compounds over time, meaning the system grows sharper the more information you feed it The quick setup guide: Download Obsidian, spin up a new vault, and open it up in Claude Code Feed Claude the document outlining Karpathy's wiki framework and tell it to initialize the system The AI will automatically structure three core folders: raw for source uploads, wiki for your interconnected pages, and CLAUDE to manage the engine Drop new materials into raw and give the command: "ingest this" Search and query your entire accumulated database whenever you want Total setup time is about five minutes, and you will never stare at an empty prompt window again The full walkthrough is linked below. Hit bookmark so you don't lose it

Bober_smart

24,597 Aufrufe • vor 2 Monaten

HERMES AGENT SHIPS WITH A BUNDLED SKILL FOR ANDREJ KARPATHY'S LLM WIKI PATTERN. A SELF-IMPROVING KNOWLEDGE BASE THAT GROWS EVERY TIME YOU FEED IT. mentioned this briefly in the overnight workflow article. here is the full breakdown. what it is: a self-improving knowledge base built as interlinked markdown files. unlike RAG (which rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. cross-references stay linked. contradictions get flagged automatically. synthesis reflects everything ingested so far. why this matters for Hermes memory: Hermes built-in memory knows YOU. it remembers your conversations, your preferences, your business context across sessions. but it doesn't know your inbox. or your meeting transcripts. or that article you saved last week. or the expert framework you want it to learn. the LLM Wiki solves that. THE DIVISION OF LABOR human curates sources and directs analysis. agent summarizes, cross-references, files, and maintains consistency. you drop in articles, transcripts, notes. Hermes indexes them, links related concepts, flags contradictions, updates affected pages. your knowledge base grows itself. SETUP IS ONE COMMAND the skill ships with Hermes. enable it. set WIKI_PATH in ~/.hermes/.env: WIKI_PATH=/Users/you/wiki defaults to ~/wiki if unset. then drop anything into it: "index this article into my wiki: [paste URL or text]" Hermes reads it, builds a source page, updates related entries, flags contradictions. THE OBSIDIAN ANGLE set OBSIDIAN_VAULT_PATH to the same directory. now your wiki is visible in Obsidian's graph view. nodes, links, backlinks. all built by Hermes. for headless servers: install obsidian-headless. syncs vaults without a GUI. agent writes from the server, you read on your laptop. THE COMPOUND EFFECT Hermes knows you. the wiki knows your world. combine them and the agent answers questions using BOTH contexts at once. month 1: you explain things twice. month 3: the agent references the wiki on its own. answers get sharper because the knowledge base got sharper. AUTOMATIONS THAT FEED THE WIKI set cron jobs to ingest automatically: "every day at 9am, check Granola for new meetings. add any new transcripts to my wiki under meeting notes." "every morning, scan my Gmail starred items. add anything worth keeping to the wiki." "every week, check arXiv for new papers in [your niche]. summarize and file." your wiki grows while you sleep. Hermes never forgets what gets indexed. THE LIMITATION TO KNOW unlike Hermes memory (which is conversational and lives across sessions), the wiki is a separate knowledge layer. Hermes won't pull from the wiki automatically unless you reference it or save it as a skill. best setup: build an LLM Wiki personality that tells Hermes to consult the wiki when answering strategy questions or domain-specific queries. full HERMES AGENT OVERNIGHT WORKFLOW👇

HERMES AGENT SHIPS WITH A BUNDLED SKILL FOR ANDREJ KARPATHY'S LLM WIKI PATTERN. A SELF-IMPROVING KNOWLEDGE BASE THAT GROWS EVERY TIME YOU FEED IT. mentioned this briefly in the overnight workflow article. here is the full breakdown. what it is: a self-improving knowledge base built as interlinked markdown files. unlike RAG (which rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. cross-references stay linked. contradictions get flagged automatically. synthesis reflects everything ingested so far. why this matters for Hermes memory: Hermes built-in memory knows YOU. it remembers your conversations, your preferences, your business context across sessions. but it doesn't know your inbox. or your meeting transcripts. or that article you saved last week. or the expert framework you want it to learn. the LLM Wiki solves that. THE DIVISION OF LABOR human curates sources and directs analysis. agent summarizes, cross-references, files, and maintains consistency. you drop in articles, transcripts, notes. Hermes indexes them, links related concepts, flags contradictions, updates affected pages. your knowledge base grows itself. SETUP IS ONE COMMAND the skill ships with Hermes. enable it. set WIKI_PATH in ~/.hermes/.env: WIKI_PATH=/Users/you/wiki defaults to ~/wiki if unset. then drop anything into it: "index this article into my wiki: [paste URL or text]" Hermes reads it, builds a source page, updates related entries, flags contradictions. THE OBSIDIAN ANGLE set OBSIDIAN_VAULT_PATH to the same directory. now your wiki is visible in Obsidian's graph view. nodes, links, backlinks. all built by Hermes. for headless servers: install obsidian-headless. syncs vaults without a GUI. agent writes from the server, you read on your laptop. THE COMPOUND EFFECT Hermes knows you. the wiki knows your world. combine them and the agent answers questions using BOTH contexts at once. month 1: you explain things twice. month 3: the agent references the wiki on its own. answers get sharper because the knowledge base got sharper. AUTOMATIONS THAT FEED THE WIKI set cron jobs to ingest automatically: "every day at 9am, check Granola for new meetings. add any new transcripts to my wiki under meeting notes." "every morning, scan my Gmail starred items. add anything worth keeping to the wiki." "every week, check arXiv for new papers in [your niche]. summarize and file." your wiki grows while you sleep. Hermes never forgets what gets indexed. THE LIMITATION TO KNOW unlike Hermes memory (which is conversational and lives across sessions), the wiki is a separate knowledge layer. Hermes won't pull from the wiki automatically unless you reference it or save it as a skill. best setup: build an LLM Wiki personality that tells Hermes to consult the wiki when answering strategy questions or domain-specific queries. full HERMES AGENT OVERNIGHT WORKFLOW👇

YanXbt

30,804 Aufrufe • vor 4 Monaten

Tested this workflow myself and the results are pretty impressive for <10 minutes of work

Tested this workflow myself and the results are pretty impressive for <10 minutes of work

Dan Scalco

153,006 Aufrufe • vor 1 Jahr

i genuinely can't understand why this isn't the first thing every claude user builds... andrej karpathy, co-founder of openai, quietly solved the exact problem making your ai useless and almost nobody noticed here's the problem he solved... every session claude starts from zero, rereads the same files, forgets every contradiction it already caught, burns tokens relearning what it knew yesterday, forever 1. raw holds the truth once, wiki holds the compiled answer forever, instructions hold the one rule that stops it from ever getting messy again 2. claude opens a raw file exactly one time in its entire life, after that it only speaks in wiki pages with the sources already cited 3. the moment claude catches you contradicting yourself, it writes both versions into the wiki with dates, so it never asks you the same wrong question twice your raw files are disposable... the compiled wiki is the only thing that actually compounds full breakdown is in the article below

i genuinely can't understand why this isn't the first thing every claude user builds... andrej karpathy, co-founder of openai, quietly solved the exact problem making your ai useless and almost nobody noticed here's the problem he solved... every session claude starts from zero, rereads the same files, forgets every contradiction it already caught, burns tokens relearning what it knew yesterday, forever 1. raw holds the truth once, wiki holds the compiled answer forever, instructions hold the one rule that stops it from ever getting messy again 2. claude opens a raw file exactly one time in its entire life, after that it only speaks in wiki pages with the sources already cited 3. the moment claude catches you contradicting yourself, it writes both versions into the wiki with dates, so it never asks you the same wrong question twice your raw files are disposable... the compiled wiki is the only thing that actually compounds full breakdown is in the article below

kai

379,491 Aufrufe • vor 2 Monaten

CLAUDE + OBSIDIAN + KARPATHY'S LLM WIKI = A WIKI THAT MAINTAINS ITSELF run this once and your research compounds instead of evaporating sources go in, a wiki comes out, and a loop keeps it honest • three layers, one owner each > the schema - CLAUDE.md, you and the agent co-evolve it > the wiki - markdown the agent owns. it writes, you read > raw sources - immutable, read only, never edited • three operations on repeat > ingest - read the source, write the summary, log one line > query - answer with citations, file it back as a new page > lint - contradictions, orphans and dead links caught early RAG re-derives the same answer from raw chunks on every query. you pay for that thinking again, every time you ask this wiki gets written once and stays current. 10-15 pages per source, nearly 100 sources on the index alone month one it saves you an hour a day. month six it knows your field better than the person you're up against for the senior seat "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase" - Andrej Karpathy the stack: 📁 Obsidian ↳ 📁 Claude ↳ 📁 Karpathy LLM-Wiki ↳

CLAUDE + OBSIDIAN + KARPATHY'S LLM WIKI = A WIKI THAT MAINTAINS ITSELF run this once and your research compounds instead of evaporating sources go in, a wiki comes out, and a loop keeps it honest • three layers, one owner each > the schema - CLAUDE.md, you and the agent co-evolve it > the wiki - markdown the agent owns. it writes, you read > raw sources - immutable, read only, never edited • three operations on repeat > ingest - read the source, write the summary, log one line > query - answer with citations, file it back as a new page > lint - contradictions, orphans and dead links caught early RAG re-derives the same answer from raw chunks on every query. you pay for that thinking again, every time you ask this wiki gets written once and stays current. 10-15 pages per source, nearly 100 sources on the index alone month one it saves you an hour a day. month six it knows your field better than the person you're up against for the senior seat "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase" - Andrej Karpathy the stack: 📁 Obsidian ↳ 📁 Claude ↳ 📁 Karpathy LLM-Wiki ↳

Annatar.md

16,939 Aufrufe • vor 1 Monat