Feb 23, 2026 · 58m · startup-ideas
How I Use Obsidian + Claude Code to Run My Life
0:00 / 0:00
▶ Watch on YouTube →
gold bands on the timeline = statements, start to end. Hover to read, click to jump. CC turns on captions
Host Greg Isenberg and guest Vin demonstrate how integrating Obsidian's networked Markdown vault with Anthropic's Claude Code command-line interface transforms a standard note-taking system into an autonomous cognitive thinking partner and personal operating system.
How this conversation actually went
Every chapter scored 0–10 on four independent dynamics. Hover any point for the reasoning behind the score. Greg holds 21.5% of the talking time here. How this is scored →
Greg as informed peer 3.8 Guest teaching 5.9 Guest disagreement 0.7 Greg pushing back 0.9
speaking balance: gold is Greg, purple is the guest (3 minute bins)
Sharpest disagreement ▶ 33:25 Rejecting AI-Generated Vault Entries
Vin firmly resists the idea of letting AI write autonomously into his vault files, asserting a strict principle that personal thought data must remain unpolluted by LLM hallucinations.
Hardest push from Greg ▶ 10:27 Challenging Practical Output ValueGreg cuts straight through the visual intrigue of Obsidian graph nodes to demand how networked notes actually produce superior work output.
Biggest teaching moment ▶ 10:37 Exposing Graph Structure to LLMsVin details how the Obsidian CLI enables Claude Code to trace latent relational structures across disparate domains that a human user could never map manually.
Greg holds their own ▶ 55:40 Reframing Memory vs TokensGreg asserts his own conceptual model, persuasively arguing that static markdown files serve as perfect, bias-free human memory and the true fuel for LLMs.
the scores for every segment, with the reasoning behind each
| Chapter | Topic | Greg as informed peer | Guest teaching | Guest disagreement | Greg pushing back | Why |
|---|---|---|---|---|---|---|
| Setting the Stage: AI as an Active Thinking Partner | 4 | 5 | 1 | 1 | Vin demonstrates the basics of Claude Code operating via CLI on local files. Greg interjects with relevant product intuition, defining the core bottleneck as feeding the model proper context. | |
| Demystifying Obsidian: Bi-directional Links and Networked Thought | 3 | 6 | 1 | 2 | Vin walks through Obsidian vaults, Markdown files, and bidirectional link graphs. Greg reacts playfully to seeing his own name in the vault, then presses Vin on practical utility. | |
| The Obsidian CLI Integration: Exposing Connected Knowledge to AI | 2 | 8 | 1 | 1 | Vin delivers an in-depth tutorial on Obsidian CLI, explaining how exposing the link graph lets Claude Code detect latent patterns across years of notes. Greg listens attentively as a receptive student. | |
| Live Demonstration: Tracing the Evolution of Ideas Over Time | 3 | 7 | 0 | 0 | Vin runs a live trace command showing the chronological evolution of his note-taking philosophy. Greg asks clarifying technical questions about whether the commands are custom-built. | |
| The Habit of Reflection: Writing as the Foundation for Agent Delegation | 4 | 5 | 0 | 0 | Greg asks how Vin integrates daily reflection amid modern life's busy schedule. Vin explains writing as both cognitive internalisation and the primary medium for delegating to AI agents. | |
| Autonomous Agent Execution and Privacy in the Second Brain | 4 | 5 | 1 | 3 | Vin demonstrates scheduling lookups via OpenClaw and his vault context. Greg raises a genuine privacy concern about giving autonomous agents unrestricted access to a personal second brain. | |
| Cross-Domain Synthesis: The Connect Command in Action | 2 | 6 | 0 | 0 | Vin demonstrates the connect command bridging disparate domains like filmmaking and world building. Greg listens to the walkthrough without interjection. | |
| Structuring External Notes and Preserving Human Thought Purity | 5 | 6 | 2 | 2 | Greg asks whether meeting transcripts and automated summaries should be pumped into Obsidian. Vin clarifies his strict boundary rule: agents can read and suggest, but humans must write to keep thought patterns uncontaminated. | |
| Deep Vault Analysis: Running the Comprehensive Ideas Command | 5 | 6 | 0 | 0 | While a comprehensive 30-day vault analysis runs, Greg connects the experience to therapy and coaching, arguing that AI's core power lies in connecting implicit dots. | |
| Actionable Output: Reviewing Idea Reports and In-Line Delegation | 4 | 6 | 1 | 1 | Vin reviews the structured output report, highlighting proposed tools and in-line delegation workflows. Greg appreciates the stark plain-text aesthetic while Vin points out how easily it can format into HTML. | |
| Higher-Level Abstraction: AI Engineering its Own Workflow Commands | 3 | 7 | 0 | 0 | Vin demonstrates prompting Claude Code at a higher level of abstraction to evaluate his skill level and engineer its own workflow command (the graduate command). Greg follows the recursive logic. | |
| Markdown Files as Human Memory: The Personal OS Paradigm | 7 | 4 | 1 | 1 | Greg delivers an articulate thesis arguing that Markdown files, not tokens, are the real oxygen and persistent memory of AI systems, positioning Obsidian as the cornerstone of the personal OS. |
Statements from this episode (15)
Vin: Web AI memory is uncontrollable and opaque to users
“A lot of people are using like Claude or ChatGPT on the web and it has things like memory, but you can't like control, you don't know what's in that memory, right? You don't know what it knows and what it doesn't know.”
Isenberg: Claude Code feels underwhelming because users fail to supply proper context
“Yeah, and that's sort of the problem that a lot of people are facing with cloud code is like, they're using it, and then they're saying, well, it's okay, it's not like game changing, and the issue is they don't have, they're not feeding the right context at th…”
Vin: Obsidian's bidirectional linking mirrors human associative thinking
“The reason why people love obsidian is because of these interrelationships. The idea that you could open a file and then, you know, I just open this file and then I'm like, oh, interesting. I mentioned Greg Eisenberg. I can click that and it goes to that file.…”
Vin: Obsidian CLI gives Claude Code access to vault note relationships
“It can give Claude code, not only those files that it can read and access, but it can also give Claude code information about the interrelationships of those files.”
Vin: Interlinked AI vaults can surface blind spots in thinking
“It can start to surface patterns about what you're thinking about that you are not seeing for yourself.”
Vin: AI calendar agents work better with daily note context
“If an agent has that context, you can, it can more effectively give you information about what you should do or not do, or, and it can more effectively make decisions on what should be in your calendar or not in your calendar.”
Vin: Using LLMs as thinking partners beats purely building autonomous agents
“I really, really, really like working with LLMs as a thinking partner. It's my favorite way of using LLMs. I know people like to use agents and LLMs to build things, but I really like using them to think alongside me.”
Vin: Backlinking to specific mental models beats tagging broad topic terms
“Originally I was backlinking to general terms, podcasts or physical fitness or filmmaking. I'm realizing it's not the most useful way to use obsidian. The most important thing to do is to create notes for each of my patterns, theories, projects, or perspective…”
Vin: Writing creates the context required to effectively delegate to AI agents
“Is that writing right now is a big way of how you delegate things to agents. That's like a whole new, that's a whole new aspect of it. So if you can develop a writing habit, You have a lot more context that you can pass over to an agent, which then dramaticall…”
Vin: Autonomous Agents Can Be Steered Entirely via Knowledge Vaults
“And now instead of like managing an agent or talking to another human about working on something, I just focus on managing this vault. This is like the new source. I just continually try and make it so that this vault has all of the information needed so that …”
Vin shows '/connect' command synthesizing disparate domains via Obsidian's link graph
“So there's connect, which is allow, it allows me to take two domains and connect them using the vaults link graph. So I can just say I did one here. And I just asked it to connect filmmaking and world building. And so it goes through and it reads all of these …”
Vin: Strict rule bars AI agents from writing in his Obsidian files
“I don't want an agent to write into the files. Like I could easily get it to do that. Like I could just say, like even here, I've asked it to write a description of some commands that I can talk about today, but I don't want it to make a file to do this becaus…”
Isenberg: OpenAI or Anthropic should acquire note-taking app Obsidian
“If I'm open AI or anthropic, I'm buying obsidian.”
Isenberg: Serious LLM Users Must Build On Centralized Markdown Notes
“The fact, like, that if you are using, if you are serious about Using LLMs to take your ideas and put in and get the most out of them. If you're serious about building, you know, what people are calling a personal OS and you are not using a centralized note-ta…”
Isenberg: 99.99% of People Won't Build Personal LLM Systems, Leaving Massive Alpha
“Well, what's cool about this is 99.99% of people are not going to spend the time to actually set up something like this and make it a part of their daily lives. And the alpha, so to speak, is in terms of leading a more productive, happier, healthier, Better, m…”