Claude just killed ALL Note-Taking, Planner, and Health Apps. Here is proof.
The creator demonstrates a custom-built, locally-run personal knowledge management interface powered by Claude AI that replaces multiple productivity apps including note-taking tools, planners, and health trackers. The entire system lives in a single local markdown folder, requiring no subscriptions or cloud dependencies beyond a Claude plan. The interface will be made available for free to members of their myICOR community.
Summary
The video presents a comprehensive demonstration of a custom-built personal knowledge management (PKM) interface that the creator has developed using Claude AI. After years of using various note-taking and productivity tools—including Evernote, Roam Research, Obsidian, Notion, Mem, Tana, Heptabase, and Sunsama—the creator has consolidated everything into a single local markdown folder that serves as the backbone for all personal and professional information.
The interface runs as a local server accessible via browser, meaning it can be used across devices on the same network or deployed to a VPS for remote access. It is built entirely on wiki-linked markdown files, making the data portable and readable by other tools like Obsidian as a fallback. The system is organized around the creator's ICOR methodology, which structures life into key elements, goals, habits, projects, topics, and journaling.
The planning and task management component replaces Sunsama by pulling in calendar events and tasks from external tools like Todoist and ClickUp via API, presenting them in a time-blocked daily and weekly view. Users can drag tasks into morning or afternoon slots, set weekly highlights, and track available time remaining in the workday.
Knowledge management features include a visual knowledge graph showing connections between notes (compared favorably to Obsidian's graph), a whiteboard for visual thinking that replaces Heptabase, collapsible outliner-style note editing with markdown support, and a 'Discuss with AI' button that launches Claude in the terminal with the relevant note's context preloaded.
Health and lifestyle tracking features include integration of Apple Watch health data via an auto-export app, workout mapping (replacing Strava), meal photo logging processed by Claude, habit tracking tied to specific goals, blood test lab values, and mood/pattern recognition from journal entries. The creator claims 15 years of personal health data has been backfilled into the local folder.
Additional features include a document inbox for scanned physical documents organized by Claude, a deliverables folder for tracking AI-assisted work in progress, a contacts/people database, and API key management stored in a local .env file. Backups are handled via Time Machine or optional cloud backup (not sync) services like Dropbox or iCloud. The interface is planned for free release to the myICOR community.
Key Insights
- The creator argues that building a PKM interface from scratch using Claude is superior to using Obsidian with AI plugins, because a custom build is not constrained by whatever Obsidian provides and offers full control over functionality and visualization.
- The creator claims that the 'Discuss with AI' button intentionally opens Claude in a terminal rather than embedding a half-baked AI interface in the app itself, so users benefit from their full Claude subscription (Max or Pro) rather than paying extra tokens through a third-party tool like Heptabase.
- The creator states that Claude Code, not Claude's Cowork interface, is the appropriate tool for non-coders and business professionals managing complex local folders, arguing that Cowork is simply a stripped-down version of Claude Code and that professionals who switch to Claude Code never go back.
- The creator describes an automated health data pipeline where an auto-export app sends Apple Watch data to a local folder daily, and Claude updates a local health database from it, meaning 15 years of personal health data—including workouts, nutrition, weight, and lab values—is stored and analyzed entirely locally without uploading to third-party health platforms.
- The creator emphasizes that the interface is purely a visual representation layer with no proprietary functionality or backend dependencies—all data remains in plain markdown files, so if the interface breaks, the user can immediately fall back to Obsidian or any other markdown-compatible tool without data loss.
Topics
Transcript
[0:00] what I'm about to reveal in this video is not only something that many of you have been asking for for months already But it's literally something that I've been dreaming of my whole life. If you follow this channel, you know it's all about productivity as a professional, how we c- become better, what tools we use And on this journey, I used endless options of personal knowledge management tools and note-taking apps. I started all the way back with Apple Notes on the iPad Notability, GoodNotes, and so on Used Evernote heavily. migrated things to Roam Research and then to Obsidian, eventually [0:33] ended up in Notion and went from Notion to other tools like Mem, Tana,…
Full transcript available for MurmurCast members
Sign Up to AccessMore from ICOR with Tom | AI Productivity
Obsidian is the tool I teach in. Keep the one you have.
The creator addresses criticism about switching to Obsidian after previously promoting other tools, clarifying that his tool-agnostic ICOR methodology remains unchanged and that Obsidian is simply an interface layer for his folder-based system. He emphasizes that the underlying folder structure, AI automation, and productivity principles are identical regardless of which tool visualizes the content.
Claude sucks. And here is why.
This video explores why Claude and other AI models produce inconsistent results, examining how model selection (Haiku vs Sonnet vs Opus vs Claude 3.5 Fable), effort levels, prompt clarity, and system context dramatically affect output quality. The speaker demonstrates these differences through a Venn diagram creation task and advocates for using organized folder systems with documented SOPs and code-based solutions to ensure consistent AI performance.
Claude can now prompt its own SESSIONS. I built the boss.
Claude now has the ability to interact with multiple sessions, allowing a streamlined orchestration of tasks through an agent called Larry. This integration can simplify task management and enhance productivity by enabling a single main session to oversee various sub-sessions or tasks.
I switched off Claude's memory. My folder does it better.
Tom explains why he disabled Claude's native memory feature and instead built a local folder-based system (myPKM) to maintain persistent context with AI agents. He shares an audit revealing systemic issues like contradictory documentation, forgotten rules, and parallel session conflicts, then outlines how to systematically fix these problems using the ICOR productivity methodology.
I do not download invoices anymore. My folder and Claude do it.
The speaker demonstrates how he uses AI (Claude) integrated with his local folder system to automate invoice collection for his accountant, downloading 36 invoices in 5 minutes with minimal manual intervention. He explains his AI team methodology, work streams, and how persistent local knowledge bases enable AI to handle recurring tasks independently without constant re-explanation.