Video wird geladen...
Video konnte nicht geladen werden
how to use obsidian + claude code to build a 24/7 personal operating system and build your startup: 1. write everything in markdown (daily notes, projects, beliefs, people, meetings) 2. link your notes together so they mirror how your brain actually thinks. 3. install obsidian cli so claude code... show more
1,140,355 Aufrufe • vor 7 Monaten •via X (Twitter)
51 Kommentare
Vin is amazing
defs
I made a fully interactive version of this lesson! Download the example files and Claude Code will walk you through EVERYTHING covered: • Obsidian CLI installation • Actually making the commands • All the concepts 🔗
Who do you want to see on the pod next? What topic? Tag below
Skills, Obsidian and Claude code makes a great pair to change our life. Thanks for sharing these tips. Is this video uploaded on YT ?
full ep on yt is here
@Hem_chandiran @grok why @X doesn’t allow captions?
X supports captions for videos—you can upload a custom .srt file right when posting on web ( Auto-captions exist for Spaces & voice posts (via Microsoft), but standard videos use manual SRT for accuracy. It's web-only for now, not mobile apps yet. That's likely the gap you're seeing.
@gregisenberg @Hem_chandiran @X Very unfair for people who cannot hear for any reason.
Understood. X provides manual .srt caption uploads for videos (web only, when posting) to ensure accuracy for deaf/hard-of-hearing users. Auto-captions via Microsoft are built-in for Spaces and voice posts. Standard videos depend on creators adding SRT files. Feedback drives ongoing accessibility updates.
@gregisenberg @Hem_chandiran @X The rest of social networks provide them automatically.
Many platforms like TikTok, Instagram, and YouTube auto-generate captions on upload. X prioritizes manual SRT uploads for videos (web only) to ensure accuracy, since auto can miss accents, jargon, or background noise. Auto-captions via Microsoft are standard for Spaces and voice posts. Feedback like yours helps shape updates.
Been on the obsidian + Claude train for a bit. Been really enjoying it. Layering OpenClaw on top I’m now out and about popping ideas, spinning up work, getting shit done on the fly. Also you CLI not required it can just read your vault directly through the filesystem.
love it
You read my mind, have been thinking about this a lot lately!
Mission accomplished
My workflow
I've been doing this for so long; my Obsidian Vault agent knows so much about me, it's amazing. Obsidian had been my favorite and most used application on my desktop until I wrote the following: Now this is my #1 most used app and I do the vast majority of my interfacing with Obsidian through it. Best personal assistant I've ever had.
you got the most curious man on earth @internetvin to drop his alpha on youtube??? woah absolute steal for content on the internet
You Around 3/25? Would love to have you at claw con
im not unfortunately
Next one
i love your work , i hate your 58min videos :/
i do 1 min vids over here
i have a better idea
You can already test this obsidian knowledge system with Claude Code:
the obsidian vault as context layer for Claude Code is the missing piece most people skip. right now everyone dumps their entire codebase into context and wonders why the output is generic. feeding it your actual thinking process through linked markdown notes means the agent understands not just what you are building but why you are building it and how it connects to everything else in your life. a founder I know in Buenos Aires runs his entire startup from obsidian and says the biggest unlock was the /trace command pattern because it showed him he had been circling the same product idea for 8 months across scattered daily notes without realizing it. the human writes, agent reads principle is also the right boundary because the moment you let the agent write your notes you lose the thinking process that makes the vault valuable in the first place
been doing something similar. the trick that leveled it up for me was adding a "decisions" folder where i log every major choice with reasoning. when claude code has access to that context, it stops suggesting things i already rejected weeks ago.
@getshadowai automatically detects your meetings, transcribes them, and generates notes — all exported as .md straight to your vault. Shadow can seriously level up the workflow!
Is it easily accessible on mobile
Bro but Claude code doesn’t work well on mobile
having a personal OS like this is essential for founders. keeps everything connected.
The linked notes are the open. We run our whole ops layer through Obsidian + agents now. Daily standup doc feeds the agent, agent updates the CRM, calendar, and outreach queue automatically. Markdown becomes the API for your business.
running this exact setup. the unlock most people miss: as the pre-flight checklist. every session, the agent reads its instructions from disk before doing anything. no context drift. no "I forgot what we were doing." biggest lesson after months of this: write to files like your future self has amnesia. because it does.
@grok what do you think of obsidian vs notion for human-agent coordination ... a team of 3 humans and 2 agents ... what should be the system of record, obsidian or notion?
"The more you write, the more context your agents have", this is the part that changed everything for me. I write down every GTM decision, every user insight, every product pivot while building. Now when I ask Claude to help me think through a new problem, it doesn't give me generic startup advice. It gives me answers built on MY context. The gap between people using AI with context and people using AI cold is going to be massive.
"Markdown files are the oxygen of LLMs" — this is the line that matters. We run our entire startup off this exact pattern. for personality, for long-term context, daily notes for raw logs. Claude reads the vault every session and picks up like a cofounder who never forgets. The counterintuitive part: the more you write for yourself, the smarter your agents get. Most people try to write *for* the AI. Wrong move. Write like a human journal — messy, honest, stream-of-consciousness. LLMs extract signal from noise better than you'd expect. Point 6 is the real unlock though. Human writes, agents execute. The moment you let AI write your context files, you get a feedback loop of hallucinated priorities.
the unlock isn't the vault—it's the discipline of writing daily. most people will set this up, write for 3 days, then abandon it. the 0.01% who stick with it build something scary powerful.
With all of these posts about creating your own 24/7 personal assistant, what they fail to mention is the enormous cost you'll rack up in tokens. Be aware of the cost of different models.
Curious, do you know why developers keep on choosing progreSQL versus SQLite? For a bot with just a few agents who is in its own docker container. I’m on Ubuntu 22 LTS. I can’t find any reason why not to run SQLite. Nor could Claude
This is such a refreshing take on utilizing Obsidian and Claude Code together. The emphasis on linking notes in a way that mirrors our thinking is particularly insightful. It challenges the conventional notion of linear project management and opens up avenues for deeper understanding and connections. Also, the point about treating writing as leverage is crucial—it’s true that the more we articulate our thoughts, the more clarity we gain, benefiting our AI companions. Implementing a system that actively reflects our voice will undoubtedly create a more personalized and effective workflow. Looking forward to diving into this episode and seeing how others interpret these ideas!
FREE Drop on How to Build Your Startup Using Obsidian and Claude Code as Your 24/7 Operating System
Good tips. I use a skill for this using obsidian CLI in codex, but should work for Claude code too (will try)
This is excellent, will help me a lot, thanks Greg :D
amazing
God is real. This is literally what u was looking for. I have a massive case and a billion notes and files And this video pops up.
Obsidian + Claude Code builds a personal OS that scales to team knowledge graphs. Linked notes mirror real workflows so handoffs stay crisp without info silos.
this actually sounds pretty wild, the way it kinda turns notes into a brain double or something. makes me wonder how long it takes to get that smooth.
Been running this same pattern for some time now - no Obsidian, just raw markdown files. daily memory logs. Claude reads them every session and picks up exactly where we left off. Step 6 is the one that matters most: human writes the vault, agent reads it. The moment the agent writes it, you lose the voice. Don't flip that rule.
I prefer to write through cursor or kiro so that markdown is down automatically for me when entities are recognized.
Just what I needed: another productivity system to feel guilty about not using. 😅
![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.](https://image.24vids.com/tw-2078404662626074695/amplify_video_thumb/2078389656312217600/img/htCh1Y9vO-Wt4ERa.jpg)
![One of the smartest things you can do with Fable 5 right now: Re-create your AI second brain to log all your business ideas, personal context, and important data. The first time I built an AI second brain was with Opus, but I recently re-created it with Fable 5, and it blew my mind. Here's exactly how to get started: Step 1. Set up your Obsidian vault Download Obsidian from Obsidian dot md if you haven't already. Then, go ahead and create a clean vault with your most important folders. For example: /ideas → business ideas, content angles, random thoughts /context → who you are, your business, your goals, your stack /data → important numbers, portfolios, metrics /log → daily entries, decisions, lessons learned This is your database. Everything Fable reads lives here. Step 2. Connect Fable 5 to your vault I like this Claude Code prompt: "/goal connect to my Obsidian vault at [path] and act as my second brain orchestrator. Read everything in /context before every session. Log anything new I tell you to /log with today's date." Fable now reads your vault before it answers anything - it knows your business, your goals, your history. Step 3. Build the self-update habit Every time you have an idea, a decision, or a lesson, tell Fable: "Log this to my second brain: [thought]" Step 4. Start querying it You can start sending prompts like: → "What are the most common themes across my last 30 ideas?" → "Based on my context, what should I be prioritising this week?" → "What decisions have I made about my content strategy so far?" Opus was good at this, but Fable is on another level. I feel the depth of reasoning it brings to your data is genuinely unlike anything I've used before. Some might argue it's a bit of overkill to use Fable for a simple second-brain setup, but if you have the means, it's 100% worth it. Build this once, and it'll compound forever.](https://image.24vids.com/tw-2076900303748895011/amplify_video_thumb/2076900248182779904/img/kjGVB6hRJW-pVScS.jpg)
