A note is not an intention. It commits to memory, not to action. I really don't care about having a whole searchable, tagged database; I hardly ever look at those notes again.

At work I have topic-based Markdown notes. Sometimes I collect information about a topic for a few weeks or months, and eventually turn it into a proper guide (making guides is my job).

I also LOVE paper notebooks, because they become a beautiful timeline of sketches, to-do lists, thoughts and plans. When I finish a notebook, I scan it then throw it in a drawer.

I also use Obsidian daily notes to journal, mostly because it's easier to open an app than to write in a notebook. I don't do anything special with those notes, unless I'm trying to "debug" something happening in my life.

[0] https://strangestloop.io/essays/things-that-arent-doing-the-...

1. most recently updated notes

2. most recently created notes

3. notes I've added to my favourites

On top of a search bar that doesn't suck, this is pretty much all I ever need.

As for "AI", it's never going anywhere near my notes. It's supposed to be my second brain filled with content I've bothered to write down for myself. "AI" doesn't write it, "AI" doesn't process it, and I will never be convinced to change that. I use "AI" extensively, but this is a hard line that I will never cross.

It is basically a server/data store and client agents, currently the agent is only for linux end user devices. The agent records evdev events (keystrokes/mouse movement), currently active window, clipboard history, shell commands issued and browsing behaviour. It runs as its own user and different functionality is compartmentalized into their own processes. Data is encrypted at rest. I'm still looking into how to best handle sensitive data in-memory at runtime.

It stores these events in a persistent queue on the clients and one-way syncs it to the server. If a client is offline for a bit it syncs it when it comes back online. As such, I am also trying to minimize storage used.

The idea is that rather than overwhelmingly linking stuff manually, e.g. with obsidian, locality of reference seems more useful as a baseline. In this data set, links by time are valued the most. In the future I'd like to add also the screenshot/video feature using hashes and perceptual hashes or an RDP like way to store as little data as possible.

For now I'm mostly in the architecting phase but I do have an early working version. Really looking for suggestions architecture wise too. So far I came up with my own binary format to save events on the clients but I'm unsure if it's the right way to go. There are many challenges to be thought about, such as changing hardware configuration (display plugged in), protecting against statistical analysis (e.g. keystroke bursts), deletion of data across sources if required, how to make sure the system can run smoothly for a decade, etc.

I collect interesting links/pages/stuff by emailing myself notes about them. I never actually _do_ anything with these notes, but from time to time I open the "Notes To Self" folder and skim through them. Anything that seems worthless I delete, anything that seems obvious I delete, the rest just sit there.

And that's more useful than you'd think - by reviewing them semi-regularly, you're indirectly memorizing their contents and refreshing their presence in your short term memory. And that to me is the benefit - not "copy this cool thing", but "feed my mind cool ideas until it has digested them and incorporated them into the gestalt.

So for me, an AI that suggests stuff would be annoying. An AI that could take some vague search terms and my history and could pull old information out of notes that don't necessarily have the keywords I enter, using the context provided by my history might be useful. So for example, I may remember I happened across a design for the DSP algorithms in guitar pedals, but the URL or note may not even mention DSP, so something that could turn a search for "guitar pedal DSP" into finding a link for an audio processing web page I visited would be useful. The AI would probably have to scan all the web pages I visit to be able to store enough context to be useful for a search like that. Doing this for 20 years or more might run into some scalability/cost issues.

The key is using it to solve problems you actually have, rather than problems you want to have.

I was losing track of people's contact details --> I made an addressbook in obsidian.

I wanted to track my exercise to find out how much I was running each week --> make graphs

And so on. Your obsidian should get a bit messy before you try to impose order on it. Use it to solve a problem badly (Just writing down how far I run in a daily diary note) then improve (Writing a query to turn all of those notes into a graph).

Personally I don't use any AI with my knowledge base. Good searching tools and a little bit of organization are the most useful thing for me.

Personally, I think keeping lots of notes/links is a kind of digital hoarding. Just like real hoarding, it's an emotional problem not an organizational problem. If you can work out what emotional need hoarding links is fulfilling for you then you're on the way to working out how to get that emotional need fulfilled by something else.

On the other hand, for work that I do day to day, I do take notes and those are a different type. Those are tied to actions I'm taking and I'll sprinkle them with actual to-do lists that I check off in the notes. I'll link ideas that are related and document things, but for my own projects, I don't try to make it too formal or strict. The notes aren't the goal, they're sort of a scratchpad for day to day operations.

One of the things I keep is the list of stuff I did during the day for when the standup call comes. Sometimes I forgot of mention a lot of stuff.

Then a few weeks ago I build the MVP of a note taking app specifically for this purpose: what did I do, what am I doing next, am I blocked by something?

No backend, data is stored in browser local storage, quick to load, a weekly summary and data export. No tracking whatsoever.

Not ready yet, which is why I didn’t do a Show HN feature yet, but has been useful to me even in its current state.

It lives at https://tinyleaps.app

Focus is supposed to mean you have a clear idea of who you are and what you need to work on, and also what you don't.

So I've taken to follow a (bespoke) process where I identify what my own personal principles are, and what priorities and efforts they imply. Then, of all the "oh I could/should do this" potential tasks that occur to me, I have an out: if it doesn't align with my own personal focus, then I can delete it.

I also have similar thoughts on turning writing into action and re-entrance, would be interested to hear your thoughts:

https://blog.sao.dev/2025-threads/

This has proven to work well for me, but I’m chafing with git and agentic coding abstractions and looking for a unifying concept. Agent of empires doesn’t feel quite right, but is in the right direction.

A simple example is YouTube. I save videos to watch later because I am not in the right headspace at the time. Then I avoid them completely. I think part of the resistance is that I know watching them properly will demand attention and probably lead to follow-up work, and I am rarely in a mode where I want that interruption.

I have thought about the whole “second brain” idea, but I worry it would just become a dumping ground. Nothing would really resurface when it actually matters. I would mostly be relying on myself to remember that I once made a note about something when I happen to be working on a related problem.

Lately I have been thinking about the idea of a passive, radio style feed that summarises the information I have collected and plays it back to me, so I can at least consume each item once.

You see those TV shows about people who hoard. They cannot throw things away because they might be important one day. This feels uncomfortably similar.

Maybe the real problem is not how we store information. Maybe it is that we aren't filtering hard enough on what is actually worth keeping in the first place.

- Workflowy is great for taking notes in meetings, allowing ad-hoc moving things around. It’s also great for reference material (what was that long command SQL query I use). But yes it’s also a graveyard.

- AirTable worked somewhat to keep moving projects forward, without growing unbounded. But only when there is a workflow. That looks like: dump tasks into rows, then create the steps as views of those tasks with different filters. So tasks essentially move systematically from uncategorized, no time estimate, no schedule, to getting tagged with all of that, and then I can narrow it down to see just what’s on the agenda for today’s date. I also have it show the sum of estimated time per date, because I inevitably end up scheduling 30 hours of tasks for a day, so that helps keep me honest on what’s achievable. I did the same thing in Workflowy with custom JavaScript but AirTable seemed more effective for this. Tasks also get linked to project buckets, and I basically then just try to keep every bucket moving forward (don’t let any active bucket get starved).

- I could throw all of this into an LLM and have it tell me what I should be working on, remind me about what I’m forgetting, and so on. But I’m basically not interested, because I’d have to give it additional context that would be beyond what I’m interested or allowed to share. Like, I’ll ask a generic question for advice to an LLM but if an LLM is going to remind me to ”call Robert about Project Mayhem, then it needs to know about Robert and Project Mayhem.

Finally extracted the data for these hashtags and fed it to an LLM to organize. I'm happy with the result https://xenodium.com/film-tv-bookmarks-chaos-resolved

I organize notes by tags, folders, and links from tree of "map of content" notes. Those documented as rules for AI. All notes came to "Inbox" folder, and from time to time I run special script that checks inbox, formats notes, tags them, and put in the most appropriate place. "git diff" to check results and fix mistakes, reset if it went wrong.

As notes organized by the limited number of well defined rules, they became easy to search and navigate by AI. Claude Code easily finds requested notes, working as advanced search engine, and they became a starting point for "deep research" : find relevant notes, follow links, detect gaps, search internet. Repeat until reach required confidence level.

The most advanced workflow so far is combination of TRIZ (Theory of Inventive Problem Solving) + First Principles Framework. Former generates ideas and hypotheses, later validates them and converge on final answer.

I "hoard" ideas and articles because it's a good way for me to offload them from my brain

As a designer, I absolutely DO scroll through my swipe files once in a while to get inspiration; sometimes I'll also go through saved github repos to borrow an implementation

E.g. that's how I ended up using a lot of libraries like Immer, Svelte, ended up loving Observable / d3js, etc.

Idk about all y'all, but notes are absolutely useful for me.

My main problem with bookmarks / notes that I forget about them. I don't need a bookmark keeping service, I need one which would bring them forward when I look for something, based on context too. Something like which also makes a plain text searchable snapshot of the page.

Not sophisticated, but it moves me forward.

[0] https://thalo.rejot.dev/blog/plain-text-knowledge-management

When I say “notes/links/docs”, I mean scattered personal inputs in general: emails, chats, bookmarks, posts, documents, repos, meeting notes, etc. The problem I’m validating is re-entry: surfacing the right context when something becomes relevant, without forcing everything to be rewritten as “notes” or adding another inbox.

If you’ve dealt with this, which source is the worst “graveyard” for you (email/chat/bookmarks/posts/docs/repos...), and do you prefer better recall/search, a pull-based digest, or a review ritual that extracts 1–3 concrete next actions?

Unfortunately I am a "write to remember" type person

My phone color notes (Android) and 70% of my screen is a note widget. This is always in my face so stuff I want to get done is at the top. Then I write on top of it kind of pushing stuff/the stack downwards.

I have a Twilio number I text to remind myself of stuff in the future by minutes/hours/days.

I've written a lot of random note-taking apps whether it's desktop, web, chrome extension... at some point I would like to unify them/central data storage

Something that did work well recently, was creating a node script to gather all text under a given wiki link and copy to a doc with some formatting modifications, and then feed the document to an LLM for consolidation and a summary of everything I have recorded for a given subject.

The ability to describe a workflow - or a production pipeline, or whatever you want to call it - but lets say, workflow, is very important in these kinds of automation systems.

You could generalise workflows such that the user is prompted to define and enforce their own flows of work, as a matter of UI/UX interaction, and see if you don't start collecting a lot of successfully executed projects...

There's a cost to recording what you're working on, so usually the only people who track it in a fine grained way are those that need exact numbers for billing. It's not worth the time otherwise.

There are hints to what people are working on. Connecting to a database means SQL may happen, but maybe not.

It's a big issue with personal assistant ideas in general. It's very difficult to get any real context on things. Even data that seems firm like calendar appointments, isn't in practice. Look at people's calendars, and you'll see them triple booked.

To answer your questions:

1. Retrieval. 90% of my notes never get touched the second time, and I can't remember them at the right time.

2. On my head + a simple task list I made.

3. Hallucinations and pricing.

> 1.Where does your “second brain” break down the most?

First and foremost, remembering to write notes or to review them. What do I want? Is there a timeline that requires things to be done before it becomes invalid or increases liability?

Secondly, remembering to do actions instead of sitting down and doing something that gives some dopamine. I decide I want to work on a project on my computer. So I go sit down in front of the computer and... I've already forgotten the project, now it's time to play a game or read Hacker News instead.

Lastly -- it's the things that I "don't know". Let's say I want to build a robotic lawnmower. There are plenty of robotic lawnmowers already but I want to build my own. I know where to find the source code (or I can make my own). I don't know where to find the tools, where to source components, or who to ask for help assembling heavy things; I don't know how to assess risks (what happens if this thing catches fire on my lawn while I'm in the kitchen? what happens if it drives into the street and hits a car? or worse, what happens if it drives into the neighbor's kids?).

> 2.What best represents “active project context” for you today?

In my head, mostly. Documents in random places like ~/Documents/<project-name>, or a todo.md in the project root. Hard to remember what <project-name> is for or when I last did anything of value for it though.

> 3.What’s your hard “no” for an AI that

If the AI does not run 100% on my machine, then it's not getting anything important. That means no notes, no personal projects that have business value. Business value includes comments or ideas to improve other peoples' products! I've seen too many times my comments end up turning into someone else's pay-me project and I see none of the rewards. Speaking of which, here I am giving you valuable information for free.

After that, it's pricing. If I spend $20 on a weekend project, that's fine. If I have to spend $20 for every task, then it'll be yet another project that is only ever half-finished.

Though I don't really have a system for storing them effectively as of yet, and as someone with a strong preference for open source on my critical workflows, I never got on the Obsidian train myself. Current experiment is Silverbullet.md, because I do very much like raw Markdown and file-based notes, but that's different from having a meaningfully fleshed-out setup haha

My understanding is that Obsidian is pretty similar? The point of my PKM isn't to turn my notes into shipped things. The point of my PKM is that when I do want to work on something, I don't have to repeat all my old mistakes to get back to where I was before, or reinvent all my own wheels.

  - task project (Todoist/Things/Reminders)
  - issues/boards (GitHub/Linear/Jira)
  - a doc/wiki page (Notion/Docs)
  - calendar
  - "in my head"

  Which one would you actually allow a tool to read?

Do I struggle to turn them into actions? No.

Do I struggle to keep them organized for later reference? All the time.

Do I use Obsidian? No.

I actually use Joplin, which I switched to after deciding I needed to dump Evernote. And before then (and somewhat simultaneously with), I used a pile of disorganized text files (sometimes shared via DropBox).

Just get filtered digests now. Needed less input, not better retrieval.

Working with other people gives you good habits against hording because you have a sense of the audience and what might be useful to them.

We also support the kanban plugin so that works well to track and share what we're working on.

hope this will help you

That being said, when I first switch to Obsidian from Evernote I noted that there is a giant community of users who use Obsidian to obsess over the perfect Obsidian setup. They don’t have any tasks to add because the only thing they “do” is micromanage Obsidian, as a hobby, to share with other hobbyists. I bet if you’re looking for an AI grift to create, this would be the group to target.

do you know if such a project already exists?

I built my own AI agent for that.

I do use it but no idea if it's an habit that will stick.

1. search & execution The problem is that if your goal is to accumulate knowledge or take notes, and you then want to use that knowledge to do something, you have to search for it yourself, and you have to think about the text in the first place. The search may not find anything that has a similar meaning to the text, or similar events, and as a result, you are unable to put it into action.

2. calendar

3. migration cost.

Good luck.

A few ruby scripts help a bit automatically cleaning them up, keeping track of their status and what not - but at the end of the day they are just text files really. I would not want to make this more complicated than that. My brain kind of is the real decider what is the main priority.

At work my 2nd brain is confluence. Most info goes into shared spaces.

Often search doesn't find what I need easily so search becomes a context switch (sub mission)

Rovo can be helpful though. Where I work has good culture of documenting things which helps.

2.What best represents “active project context” for you today?

Jira task status 80%; Plus Slack save for laters 15%; Then a confluence todo list 5%

Which one would you actually allow a tool to read?

All of them

3.What’s your hard “no” for an AI that suggests actions from your notes/links? (pick 1–2)

Activation energy to get a 3rd party AI approved in my org for compliance is enormous. Plus we dogfood our own.

It won't happen until you become the next Cursor or Loveable and even then maybe not. (we can't run CC lol!)

If someone could make an AI tool that takes all of my bookmarks and surfaces one or two insights from them to me per day, I.E., "hey you bookmarked the wikipedia page for this movie director, did you know one of his movies was just added to netflix?" or "Hey, you bookmarked the Kotlin website, want to try making a Kotlin project? Here are some app recommendations based on your other bookmarks..."

First off, it doesn't seem to matter whether you maintain a Zetelkasten or an org mode system or follow GTD. There have been some very productive people that have used these systems, and there are people we still talk about 2,500 years after their death who definitely didn't use these systems.

I know a girl who knows pretty much nothing about personal knowledge management systems and puts todos as notes in her apple notes app. She's a baker. Recently she used some random LLM app generation platform to launch an app wherein you take pictures of your nails and then can put random designs on it to see what your nails would look like with that design. Last I heard, she had several thousand downloads already, in just a week or so.

I know a guy worth multiple tens of millions because he thought Bitcoin was going to be the global currency by 2016. He's otherwise unremarkable and spends his time going from regional Burn to regional Burn, getting high, and playing videogames.

I'm not sure why we use personal knowledge management systems or try to optimize our lives, I guess it probably doesn't matter. For me I'm also not sure; maybe to be as actualized as possible? Maximize the "potential" of my life? Get rich? Get famous? Get powerful (read: some combination of rich and famous)? To what end? Because I admire the changes Newton and Feynman and Torvalds wrought in the world? Did they even use these systems? Am I smart enough to have anywhere near their level of impact? Can I make up the difference with a highly tuned external brain, like Manfred Macx?

Well, it doesn't seem to matter. Stephen King has a rigidly disciplined writing schedule and is an incredibly prolific author. George RR Martin is so much the opposite he once asked King on stage for advice on being a more productive author. Both are world famous authors, both have had multiple tv shows made from their works. The only thing consistent between them is they both have some kind of output into the world, and that output happens to be really good. Now let me introduce you to some highly successful authors who write atrociously. After that I'll introduce you to some writers you've never heard of, who write a huge volume of good work but just haven't "broken through."

Cynically, it seems like we have about as much say in the outcome of our lives as a dice roll, and all the decisions we make can at most trigger a second or third roll that could end up anywhere, and whether it's a better or worse roll is uncorrelated with whether the decision was a "good" or "bad" one as we typically measure these things (I know a recovered drug addict that found success in life through a combination of using his past as inspiration to fuel not wasting any more of his life, and leveraging the connections he made when making his way through the legal / recovery system. The decision to try heroin is directly correlated with his now enviably successful life).

The interesting thing is, you can experience this for yourself, cheaply and relatively quickly. Make a play at a successful YouTube channel. Film a couple hbomberguy style deep dives into any topic that interests you, and join the hordes of video essayists clambering for Algo attention, hoarding a couple hundred to a thousand views per. After 5 years you might get a viral hit that completely turns your channel around, or not.

I guess unsurprisingly, Life is an unsolved problem. I just wish all the little experiment I try had at least a measurably positive outcome over time. It seems to not matter outside of making me feel good.

Edit: to op, I guess you're looking at different management systems, here's some explanations for how mine works. It's a sort of emotion + knowledge + network management system:

https://blog.calebjay.com/posts/in-defense-of-pen-and-paper/...

https://blog.calebjay.com/posts/my-new-life-stack/#organizat...

Capture: notion and twitter have been best, obsidian and regular markdown have been worst.

Notion is good because of how they support a calendar view where you can put documents in a day's cell, and then see a list view that's just a stack of those notes. I keep a daily diary or youarehere type doc, where I'll have checklists and notes on small things that don't merit changes to a dedicated page. There's arguably a "retrieval" breakdown in that I don't really go back through these to update them or collate them into bigger pages.

Twitter is good because it's low friction and I can just go off, which is fun, and because they have decent search, so I can quote-tweet a related thing and sort of thread the graph together. If you're talking about BASB you're probably familiar with this corner of twitter. visakanv etc. This method works well if you use it enough to be able to recall your other notes. I think there's something special about the twitter format here too: it discourages whole-page thoughts in favor of sequential pithy bits, which i think are easier to both link and recall.

Execution: I would like a chat frontend (signal/SMS/etc) where I can just talk to my projects, ask the status of things, get suggestions, etc. Push based, rather than pull based, execution.

Active project context: I've dropped todoist-like things since they're limited in what they can express, and notion/markdown can do todolists etc. I tend to have lists in markdown style that live in two places: my daily diary/todo docs, and the actual projects themselves. This is messy and it would be lovely if notion or similar had the concept of a "todo block" and could collate all of them into a single view where I could understand association, prune and dedupe, etc. Even better if there's an agent that does or suggests cleanup whenever a new block enters.

Larger projects will get docs of their own, lots of sprawl and notes etc, and then some formalization around a spec or something. I move these to an archive folder when I'm done with the notes and the final document is fleshed out, but I'd love an agent review that makes sure I'm not leaving things on the cutting board, and that I've handled all the todos etc in my notes pages.

I don't use bidirectional linking/tagging enough, but I really should, since I want to be able to coin keywords for particular concepts inline, and then be able to access their overview and see everything that mentions them in a graphlike way.

Calendar is definitely a much used component day to day. For planning, etc. But it's not a source of truth. Everything on a calendar should just be a proxy/link to a more robust doc.

Hard nos: My take on privacy policies for things like this is "show me your incentives and I'll show you your outcomes". That is to say, any company that can survive an attempt to profit from data fuckery will do so. Your data retention policy should include technically unambiguous red lines that are not to be crossed, and define specific per-user monetary payout in the event that a breach occurs, to include clauses that cause user payout to occur before eg preferred stockholders get liquidation preference and drain the possible payout pool. Routine third party audits of how user data is handled/retained/distributed etc. I recognize that this is a bit unhinged, but that's what signaling credibility looks like. A company says "we won't sell your data" and I say "or what" and there's hemming and hawing because nothing will happen to them. If the answer is "this company dies on the spot and our investors get completely fucked", now we can talk.

I think AI service pricing applies here: generally, if it seems neat I could be in for $20 easy, and if it's genuinely game changing, $200/mo is completely reasonable to ask.

re Migration cost: I expect to be able to get 100% of my data in a reasonable non-proprietary format. If that's some blend of markdown, json, sqlite, whatever, fine.

But the bottom line for me, where does my second brain break down the most? It doesn't talk back to me. I want it to understand what I've got going on, and my idiosyncracies. I want to present it with new information and have it be like "oh, this relates to X" or, periodically, to pop up with something like "I'm noticing this correlation / related idea in areas X, Y, Z... does that resonate? Is there something here?" Again, push vs pull. My second brain should be a proactive chatbot. "Noise" is so often thought about in terms of frequency, but it's really about insight quality. If my response to 80% of push notis is "damn, good call" then you can send one every 5 minutes.

I also hear no mention of one's personal life. I don't really make the distinction. It's all in there. I should be able to bitch to this chatbot about my manager, have it know about that background, and riff with me to navigate hard convos. I should be able to talk to it about side projects I have going on, and let it thread those into my calendar. Etc. Notion is already an adequate second brain for work. Nobody has yet built an adequate second brain for the home. My house, my relationship(s), my side projects, my own diarying and self reflection... these are the contents of my brain that matter.

Email in bio if you want to talk. I'm a design technologist and happy to riff / give feedback.