正在加载视频...

视频加载失败

返回首页

CLAUDE + OBSIDIAN + LOOP ENGINEERING = A VAULT THAT RUNS ITSELF the core idea: the loop keeps its state in the vault, so the chat window can close anytime everything Claude knows lives in a markdown file the loop: > capture - a thought lands in 00-inbox >...

polydao's profile picture

Mr. Buzzoni

26,427 subscribers

29,485 次观看 • 4 天前 •via X (Twitter)

教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

14 条评论

Hussain Hashim | Building SundayBack 的头像
Hussain Hashim | Building SundayBack4 天前

@polydao love this setup. I'd add a step for regular vault audits. Helps keep the chaos in check and ensures your markdowns don't get too cluttered over time.

Argona 的头像
Argona4 天前

damn this is the kind of thing people screenshot and keep coming back to

Rix 的头像
Rix4 天前

dummy version 🫖: obsidian = a notebook on your computer claude = the assistant that writes in it the "loop" = claude writes a draft on a separate page first, another ai checks it, and only then it goes into your real notebook basically: never let the ai write straight into your notes without someone checking. that's the whole post 😃😉

Yohaku 的头像
Yohaku4 天前

Claude + Obsidian + Loop engineering looks good actually

Jack 的头像
Jack3 天前

先装review闸,别的慢慢说

macintosh 的头像
macintosh4 天前

A loop that re-reads its vault on every wake-up pays for it in input tokens. A 50k-token vault on 24 hourly runs is 1.2M tokens a day before it does any work.

女战士 互关版 的头像
女战士 互关版4 天前

claude加obsidian这个组合我用了小半年，说实话最爽的不是loop自动跑，而是“chat window可以随时关掉”这点。以前跟模型聊到一半关网页就全丢了，现在每个想法落在00-inbox里，第二天打开还能接着往下推。不过我得吐槽

Clifford Bernard 的头像
Clifford Bernard3 天前

@grok, what is this music?

Archive 的头像
Archive4 天前

how about Obsidian + JEV? that would be a pretty nice combo as well

Sarah Satonov 的头像
Sarah Satonov4 天前

vault-as-state is slick, close chat anytime and loop survives. markdown as memory layer way underrated. been running something similar for notes, the inbox→context handoff is where most setups break

拾光的 AI 应用观察 的头像
拾光的 AI 应用观察3 天前

状态放vault里这个思路对，聊天窗口一关上下文就没了确实是硬伤。但markdown当状态机跑久了会乱，得配个schema约束下字段，不然Claude自己都能读串

Dmytro | Finance & Crypto 的头像
Dmytro | Finance & Crypto4 天前

55% → 72% → 84% on what eval, and how many samples? Jumps that size on a small test set can be mostly noise.

Ayush Barnwal | Building 的头像
Ayush Barnwal | Building4 天前

the vault surviving the closed tab is the right shape but it still only survives inside that vault... open chatgpt and the graph is gone

cortexch 的头像
cortexch4 天前

who reviews the critic tho? if both agents are the same model they make the same mistakes

相关视频

KIMI K3 + OBSIDIAN + LOOP ENGINEERING = A VAULT THAT RUNS ITSELF the core idea: the vault is the loop's state, not the chat window everything Kimi K3 knows lives in a .md file the loop: > capture - a thought lands in 00-inbox > context - K3 pulls links, tags, and neighbouring notes > draft - edits happen inside a git worktree, never the live vault > review - a critic agent checks the diff before anything ships > commit - appended to the vault, nothing gets rewritten the key insight: frontmatter fields like supports, contradicts, and supersedes are graph edges, not metadata - the note format is the write API start with a plain loop, it runs about 2-4x the cost of one direct call > only move to a full graph once state has to outlive the session, several agents need to coordinate, or you have to explain what changed - that jump can run 10-50x one review assistant climbed from 55% to 72% to 84% just by moving through these shapes in order
0:20

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

Mr. Buzzoni

10,680 次观看 • 1 个月前

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
0:24

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

58,643 次观看 • 4 个月前

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 次观看 • 1 个月前

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this
0:21

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this

Yarchi

32,594 次观看 • 3 个月前

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 次观看 • 2 个月前

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.
4:19

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

DegenCalls

20,124 次观看 • 3 个月前

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 次观看 • 3 个月前

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 次观看 • 2 个月前

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.
0:22

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 次观看 • 2 个月前

PSYCHO CREATED A GOD-MODE SECOND BRAIN ON FABLE 5 THAT FILLS ITS OWN KNOWLEDGE GAPS WHILE YOU SLEEP. KARPATHY'S FILE STRUCTURE MAKES IT POSSIBLE. Everyone wires Claude into Obsidian, posts the graph, and stops. this guy added a third system and it quietly changes the whole game: The full build is in the article below: vault structure, the Claude wiring, the exact prompts, the skills. > Obsidian as the knowledge base, but any notes app works as long as Claude Code can see the files > Karpathy's LLM Wiki doc as the skeleton, so the vault is organized the way a model actually reads, not the way humans decorate folders > a self-learning skill on a weekly loop: scans the entire brain, finds the gaps, then researches YouTube and Google by itself to fill them Read the third one again, actually your notes only ever contain what you happened to write down, and the gap-finder breaks that ceiling: the brain starts knowing things you never told it. Most second brains know what you told them. a real one notices what you didn't. that's the difference between note-taking and compounding. one sits there. the other gets smarter every week whether you showed up or not. P.S. send the article straight to your Claude, tell it to interview you, and the brain starts filling itself tonight.
1:05

PSYCHO CREATED A GOD-MODE SECOND BRAIN ON FABLE 5 THAT FILLS ITS OWN KNOWLEDGE GAPS WHILE YOU SLEEP. KARPATHY'S FILE STRUCTURE MAKES IT POSSIBLE. Everyone wires Claude into Obsidian, posts the graph, and stops. this guy added a third system and it quietly changes the whole game: The full build is in the article below: vault structure, the Claude wiring, the exact prompts, the skills. > Obsidian as the knowledge base, but any notes app works as long as Claude Code can see the files > Karpathy's LLM Wiki doc as the skeleton, so the vault is organized the way a model actually reads, not the way humans decorate folders > a self-learning skill on a weekly loop: scans the entire brain, finds the gaps, then researches YouTube and Google by itself to fill them Read the third one again, actually your notes only ever contain what you happened to write down, and the gap-finder breaks that ceiling: the brain starts knowing things you never told it. Most second brains know what you told them. a real one notices what you didn't. that's the difference between note-taking and compounding. one sits there. the other gets smarter every week whether you showed up or not. P.S. send the article straight to your Claude, tell it to interview you, and the brain starts filling itself tonight.

Miraqle

41,307 次观看 • 3 个月前

Head of Claude Code, Boris Cherny: "You're not supposed to write code anymore. You're supposed to build a graph that writes itself." In 30 minutes he breaks down how engineers at Anthropic build graphs that write the code, catch the bugs, and ships. The missing piece most developers skip: how to wire those agents into a graph that runs, verifies, and improves without you. Watch it, then read the full guide on graph engineering below.
31:23

Head of Claude Code, Boris Cherny: "You're not supposed to write code anymore. You're supposed to build a graph that writes itself." In 30 minutes he breaks down how engineers at Anthropic build graphs that write the code, catch the bugs, and ships. The missing piece most developers skip: how to wire those agents into a graph that runs, verifies, and improves without you. Watch it, then read the full guide on graph engineering below.

Mahax

417,474 次观看 • 2 个月前

AN ANTHROPIC ENGINEER LEAKED THIS OBSIDIAN CONVENTION you start with 12 notes and one convention. 6 months later you have 2379 and every one is linked to every one it belongs next to. you never touched the graph. claude did the convention is a domain prefix at the top of every markdown file. six characters. claude reads it, knows where the note belongs, and connects it to the older ones without you ever asking you drop in a new pdf at midnight. claude reads it, writes 8 linked notes, contradicts your old note from march, dates both versions, and pins the one you actually need on top by morning your vault stops being a folder. it becomes a night sky article in the first reply i test things like this on myself and share the results. follow kai if you want to see what's next
0:21

AN ANTHROPIC ENGINEER LEAKED THIS OBSIDIAN CONVENTION you start with 12 notes and one convention. 6 months later you have 2379 and every one is linked to every one it belongs next to. you never touched the graph. claude did the convention is a domain prefix at the top of every markdown file. six characters. claude reads it, knows where the note belongs, and connects it to the older ones without you ever asking you drop in a new pdf at midnight. claude reads it, writes 8 linked notes, contradicts your old note from march, dates both versions, and pins the one you actually need on top by morning your vault stops being a folder. it becomes a night sky article in the first reply i test things like this on myself and share the results. follow kai if you want to see what's next

kai

11,994 次观看 • 2 个月前

Andrej Karpathy, OpenAI Co-founder, introduced the "LLM Wiki" - a knowledge graph inside Obsidian i built my own version for GTM and here's exactly how you can do the same: - one vault, one folder per thing your business knows: offer, buyers, voice, market map, rooms, workflows, rulings, prospects, signals, messages, metrics - one note per fact, 50-150 words, a title you can say out loud ("a budget that can survive"), four frontmatter keys (type, tags, created, status) - every note links to its folder hub, two siblings and one note in another folder, so the graph becomes one connected web instead of eleven islands - a rulings folder where every correction you give an agent becomes one dated line, and every run reads it before drafting... a correction becomes permanent instead of repeated - Claude Code pointed at the vault reads the hubs first, greps the rulings, then drafts, and everything it learns goes back in as a note the same day - graph view colored by folder, hubs in white, so you see which cluster is thin before a workflow fails the article below teaches you how to build the full workflow step-by-step:
0:21

Andrej Karpathy, OpenAI Co-founder, introduced the "LLM Wiki" - a knowledge graph inside Obsidian i built my own version for GTM and here's exactly how you can do the same: - one vault, one folder per thing your business knows: offer, buyers, voice, market map, rooms, workflows, rulings, prospects, signals, messages, metrics - one note per fact, 50-150 words, a title you can say out loud ("a budget that can survive"), four frontmatter keys (type, tags, created, status) - every note links to its folder hub, two siblings and one note in another folder, so the graph becomes one connected web instead of eleven islands - a rulings folder where every correction you give an agent becomes one dated line, and every run reads it before drafting... a correction becomes permanent instead of repeated - Claude Code pointed at the vault reads the hubs first, greps the rulings, then drafts, and everything it learns goes back in as a note the same day - graph view colored by folder, hubs in white, so you see which cluster is thin before a workflow fails the article below teaches you how to build the full workflow step-by-step:

Machina

30,551 次观看 • 1 个月前

Knowledge management consultants charge thousands to build systems that fail for the same reason every time! They require someone to maintain them. This architecture requires nobody. One emoji reaction on a Slack message. n8n detecting the tag and triggering the downstream workflow. Claude extracting the insight, structuring it into a vault note, and writing connections to related knowledge. The structured artifact lands in a shared Obsidian vault of plain Markdown files readable by any tool without API integration or vendor lock-in. The hard-won operational insight that leaves with the person who found it now stays in the vault permanently. Bookmark this so you do not lose it! Follow NeilXbt for more n8n and Claude builds that solve the knowledge problem.
0:56

Knowledge management consultants charge thousands to build systems that fail for the same reason every time! They require someone to maintain them. This architecture requires nobody. One emoji reaction on a Slack message. n8n detecting the tag and triggering the downstream workflow. Claude extracting the insight, structuring it into a vault note, and writing connections to related knowledge. The structured artifact lands in a shared Obsidian vault of plain Markdown files readable by any tool without API integration or vendor lock-in. The hard-won operational insight that leaves with the person who found it now stays in the vault permanently. Bookmark this so you do not lose it! Follow NeilXbt for more n8n and Claude builds that solve the knowledge problem.

NeilXbt

14,798 次观看 • 4 个月前

GROK BOT WIRED INTO OBSIDIAN JUST CHEWED THROUGH 4,200 NOTES IN 9 MINUTES AND FOUND 3 IDEAS I ALREADY FORGOT I HAD X amateurs still paste prompts into a chat window and copy the answer back by hand while pros give the agent write access to the vault and walk away your second brain is a graveyard 4,200 files, 380 orphans nothing links to, a search bar as your only tool the exact architecture: point a Grok swarm at 1 vault folder through an MCP filesystem server with read and write, so the agents stop guessing from context and start reading every daily log, every clipped thread, every dead draft from 2024 force one instruction: find every concept sitting in 3+ notes with no [[link]] between them, build the MOC, wikilink both directions 9 minutes, 214 new links, 38 orphans pulled back in make it write markdown back into the vault instead of dumping to chat, so tomorrow the swarm reads what it wrote yesterday and compounds instead of resetting when you close the tab that's the whole loop read the vault, write to the vault, compound the complete automation script I spent 3 years taking notes I never read, the bot read all 4,200 in 9 minutes
0:27

GROK BOT WIRED INTO OBSIDIAN JUST CHEWED THROUGH 4,200 NOTES IN 9 MINUTES AND FOUND 3 IDEAS I ALREADY FORGOT I HAD X amateurs still paste prompts into a chat window and copy the answer back by hand while pros give the agent write access to the vault and walk away your second brain is a graveyard 4,200 files, 380 orphans nothing links to, a search bar as your only tool the exact architecture: point a Grok swarm at 1 vault folder through an MCP filesystem server with read and write, so the agents stop guessing from context and start reading every daily log, every clipped thread, every dead draft from 2024 force one instruction: find every concept sitting in 3+ notes with no [[link]] between them, build the MOC, wikilink both directions 9 minutes, 214 new links, 38 orphans pulled back in make it write markdown back into the vault instead of dumping to chat, so tomorrow the swarm reads what it wrote yesterday and compounds instead of resetting when you close the tab that's the whole loop read the vault, write to the vault, compound the complete automation script I spent 3 years taking notes I never read, the bot read all 4,200 in 9 minutes

Spike 1%

26,778 次观看 • 1 个月前

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below
0:20

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

rari

20,934 次观看 • 2 个月前

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite
0:20

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

elune

16,875 次观看 • 2 个月前

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.
0:37

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 次观看 • 3 个月前

Obsidian + method Karpathy + Claude Code = a quantum second brain that talks back. Most second brains are graveyards you clip 300 articles, tag 80 notes, build a graph that looks like a galaxy, then never open it again. Karpathy fix is stupid simple: 1 file, append only, new thought on top, review by scrolling no folders, no tags, no 40-minute “PKM setup” videos. The capture layer is 1 Obsidian vault with 1 file called stream md, where every idea, quote and link lands in under 10 seconds, because anything slower and you quit by day 4. Once a week Claude Code reads the whole vault from the terminal with 1 prompt “find the 5 ideas I keep circling without noticing” and sees patterns across 6 months you can’t hold in working memory. Instead of searching keywords you ask questions like “what did I think about agent pricing in March,” and Claude greps 4,000 notes and quotes your own words back with file paths. Then the vault becomes context drafting a post, a pitch or a spec, Claude pulls in your past thinking instead of generic internet mush, and your output starts sounding like you, compressed. The first week feels pointless at 20 notes, month 1 brings the first “wait, I already solved this” moment, by month 3 Claude connects 2 notes written 70 days apart and that connection becomes your best post of the year, by month 6 you stop asking Google things you already answered. The whole setup costs $0 in software and 1 evening. Notion sells you a workspace, Obsidian gives you files, Claude gives them a voice. Everyone rents a second brain this one lives on your disk and grows. You wrote the notes, and now something finally reads them.
0:27

Obsidian + method Karpathy + Claude Code = a quantum second brain that talks back. Most second brains are graveyards you clip 300 articles, tag 80 notes, build a graph that looks like a galaxy, then never open it again. Karpathy fix is stupid simple: 1 file, append only, new thought on top, review by scrolling no folders, no tags, no 40-minute “PKM setup” videos. The capture layer is 1 Obsidian vault with 1 file called stream md, where every idea, quote and link lands in under 10 seconds, because anything slower and you quit by day 4. Once a week Claude Code reads the whole vault from the terminal with 1 prompt “find the 5 ideas I keep circling without noticing” and sees patterns across 6 months you can’t hold in working memory. Instead of searching keywords you ask questions like “what did I think about agent pricing in March,” and Claude greps 4,000 notes and quotes your own words back with file paths. Then the vault becomes context drafting a post, a pitch or a spec, Claude pulls in your past thinking instead of generic internet mush, and your output starts sounding like you, compressed. The first week feels pointless at 20 notes, month 1 brings the first “wait, I already solved this” moment, by month 3 Claude connects 2 notes written 70 days apart and that connection becomes your best post of the year, by month 6 you stop asking Google things you already answered. The whole setup costs $0 in software and 1 evening. Notion sells you a workspace, Obsidian gives you files, Claude gives them a voice. Everyone rents a second brain this one lives on your disk and grows. You wrote the notes, and now something finally reads them.

West Lord

69,488 次观看 • 2 个月前

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.
55:30

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

MIKE

32,199 次观看 • 2 个月前