Looks interesting but is in desperate need of an explainer video or some GIFs or something to showcase what it is doing. I'm not going to go through all the trouble of downloading and connecting to my OpenAI api key/Obsidian library without having a better grasp of what exactly it is doing.
I would very much appreciate the same for RUNE if you feel motivated.
I'm looking now to choose the obsidian plugin that helps me take advantage of the vast amount of notes I have created with obsidian over the last few years.
Best of luck. We need more of such tools in this note-taking and management area.
A YC Startup, Khoj[1], recently did a ShowHN[2]. It works and has several options, including an Obsidian Plugin and for Emacs. Unfortunately, it drags my computer, and I can't do anything else much once I run the local server. Perhaps, once I upgrade out of my Intel iMac, I will return to it.
Did you miss the "flexible" part of your quote? Obsidian's value proposition is not simply "private". It does a lot more than that.
Personally, I'm interested in this sort of functionality because I would like my notes to be densely cross-referenced whenever possible, automatically and intelligently.
> isn't this antithetical to the spirit of obsidian?
I think so, yeah. Kepano (CEO of Obsidian, the company) has stated that they're waiting for the technology to progress to where models can be run locally.
But I think we are there for most tasks. I thought a bit about this today and wrote a blog post about how to use a local ai tool, Ollama, to summarize, make links, and ask questions about my notes. It’s not a fully fleshed out plugin but shows the start in about 20 or so lines of typescript.
Have you tried Dendron? I'm at the point where I'm debating if I want to migrate my workflow from vscode over to emacs so I can use org-roam in a combined notes/code/documents workflow, and both dendron and foam popped up in my searching for alternatives.
I'm curious if you had any preference or reason why you went with foam.
Anyone know of something like this for Logseq? Given that it's ultimately just a bunch of markdown lists in flat files, it doesn't even seem like it would need Logseq specific integration anyway. Can one of the llama projects read notes from local files and answer questions about them?
I seem to missing something during install -- Odin is not showing up in the list of Community Plugins.
I'm running locally via docker and have tried updating the Obsidian client + toggling restricted mode + restarting.
Very excited to try it out if I can get the install to work.
Lately, my colleagues and I have noticed how difficult it is becoming to organize and structure our thoughts, ideas, and notes. As budding engineers and full-fledged graph enthusiasts, we decided to approach this problem in our style - we began to study, research and look for different tools that could help us automate and improve these processes. In the process of brainstorming and research, we have read quite a lot of scientific papers devoted to the concept of knowledge graphs. We found many of these works and other materials with the help of LLM and we came up with the idea of trying to combine these two technologies in one project that was supposed to help us with the most difficult thing - organizing yourself. Of course, besides this, we came up with many more ideas, some of which we had to shelve with great regret, and some we even managed to implement in our other projects.
Given that my colleague already had a wealth of experience using Obsidian and I made some contributions to LangChain, a very nice open-source Python framework for LLM communication, we decided to unite forces - I always enjoyed creating rich user interfaces while my colleague, Patrik, dealt with the part of the project that my UI needed to render. This is how our work on ODIN began, but what is Obsidian, how did a god from Norse mythology get in here, and why is TypeScript great? Let's find out.
Although I didn’t have such extensive experience working with Obsidian, I fell in love with it at first sight - a pragmatic and user-friendly interface, nice colors, a wide and very open open-source community and other goodies - what else does a good note-taking application need? With these thoughts in mind, I began to study how Obsidian works from the inside, how it can be expanded, and how it can be connected to other technologies - such as LangChain, in our case.
I was very pleasantly surprised when I discovered a well-made Developer API that allows you to create your custom community plugins that can easily connect to the application itself. I was even more pleasantly surprised when I discovered that all this is web-based and has support for React, which I worked with, and Svelte for its fans. Although the official documentation is not too full of details and sometimes you can get lost in it, a very convenient UI styling system and strict TypeScript type definitions, coupled with IntelliSense, which I always use, is a game-changer.
What's notable is the ease of creating plugins in real time; npm scripts allow you to instantly detect code changes, and the Obsidian Hot Reload plugin speeds up development several times. In addition, Obsidian provides developer tools like popular browsers, simplifying the debugging process by accessing the console and directly inspecting elements on the screen. This flexibility in the Obsidian API allows developers to bring their creativity to life, unlocking the full potential of Obsidian to create unique note-taking experiences and more. Honestly, it feels just like making a web application in a modern and robust environment. I'll miss this when I get back to regular web development.
That’s all great, but still, why ODIN? Honestly, it’s quite simple — we liked the project naming style that has existed in Memgraph for a long time — for example, MAGE, also known as Memgraph Advanced Graph Extension, seemed to us a damn original name, sharp as volcanic glass — and so, ODIN was born, from now onwards known as Obsidian Driven Information Network, an Obsidian plugin for knowledge management. This name became the real starting point of our project, representing the goal that we were trying to comprehend and the idea that we were trying to realize.
In our R&D process, while working on ODIN, we figured out that data storage is the core of the app's architecture, without which neither the backend nor the frontend would make any sense. Even though we thought a lot about traditional databases such as PostgreSQL, the Obsidian knowledge graph was the main inspiration to try Memgraph, a graph database that excels in modeling complex relationships and connections, making it the ideal choice for creating and navigating intricate information networks.
Even I, an ordinary student with a passion for developing user interfaces, was able to play around with both Memgraph and the query language called Cypher. I highly recommend trying the visualization that Memgraph Lab provides, even if you are far from both database graphs and software development in general.
By seamless integration with LangChain, we’ve tried to leverage Memgraph's speed and efficiency to transform standard notes into interconnected knowledge graphs empowered by the flexibility of embedding search. This enables you not only to traverse your notes effortlessly but also to extract valuable insights by interacting with LLMs through LangChain implemented in the backend using Python and FastAPI. With Memgraph as our data storage solution, ODIN redefines the way we store and harness knowledge, offering a platform for building an intelligent and dynamic personal knowledge management system just from your notes. Isn’t it wonderful?
ODIN introduces a multitude of functionalities to improve your knowledge management experience. At its core, ODIN provides a chat-like prompt bar for answering questions about the data stored in your knowledge graph as if you were just chatting with your knowledge collection.
With ODIN's advanced graph visualization capabilities provided by Cytoscape, an amazing library for graph visualization with complete TypeScript compatibility, you gain a whole new view of your Obsidian vault, effortlessly navigating through the complex web of your notes. This extends to individual files view, where you can delve deep into specific topics from your markdown notes. Furthermore, ODIN expands the Obsidian native drop-down menu by adding new advanced functions. Link prediction, as its name suggests, generates connections to other markdown files in your entire vault, enriching your note's content with thematically relevant references. Moreover, you can extract thought-provoking questions from your markdown file, fostering deeper contemplation. Lastly, the node suggestion capability enhances your note-taking by highlighting thematically connected nodes, forging meaningful connections between highlighted text and related knowledge nodes, all while promoting a more comprehensive understanding of your stored information. On the other hand, clicking the node from the file view will highlight related sentences directly in your opened note. These features perfectly represent the goals we were trying to achieve and have proven to be useful in our daily lives, which means they might be of interest to other developers as well as anyone else interested in organizing their knowledge in a better way.
The Obsidian community (including you, reading this article!) is the lifeblood of the platform's evolution and continued success. At the forefront of this community-driven ecosystem are the invaluable community plugins, just like ODIN. These user-generated extensions enhance Obsidian's functionality, addressing specific user needs and preferences. Becoming a part of this thriving community is not only about reaping the benefits of these plugins but also contributing to its growth. By actively participating in discussions, providing feedback, or even crafting your own plugins, you can play a pivotal role in shaping the future of Obsidian, enriching the collective knowledge management experience, and ensuring that this vibrant community continues to flourish.
The history of the creation of this project was long (and sometimes painful to remember), but if you were to ask me if I would do it again, I would without any hesitation. Creating plugin-type interfaces is a breath of fresh air in frontend development, which still fits perfectly not only into open-source contribution but also into professional experience along with career growth. Although this project could be done better in many ways, it will remain a reliable indicator that modern technologies can and should be used in conjunction with one another. You, too, can become a part of this story — open an issue in our GitHub repository, and we will be happy to make ODIN better together!
I hope that I was able to ignite your interest in trying Obsidian or even making a more tangible contribution to this incredible open-source community and thank you for reading this story about my journey.
Just want to say this is a great idea and while I cant dive into it now (time) Im excited to dive into this in the future. Ill hve to bookmark this and return to it
The writer and Patrik created ODIN using Obsidian to improve knowledge management, incorporating advanced features and technologies. They value the Obsidian community and invite GitHub contributions.
I ran a poll recently in a PKM community of 17,000 members asking who has written a book—or created some other knowledge product like a course—using their tool (Obsidian, Zettelkasten, LogSeq, etc.).
I received two responses of people who actually produced something.
The vast majority, it seems, are professional note-taking junkies.
People in the Obsidian forum spend their lives fooling around with metadata conventions and "tagging" and "wikilinks" instead of producing work that actually matters.
Intellectual procrastination at its finest.
Now we have this... ODIN—a way to outsource your intellectual note-taking procrastination to AI.
Note: The requirement wasn't just a book. It was any "published knowledge product" which I define as book, code, course, essay, etc. (What Naval Ravikant calls Specific Knowledge).
Why is writing long-form works the only type of output that matters?
I use my PKM to connect the ideas I've read about over time. When I come across a topic again, I can quickly review what I've learned about it in the past, and how it connects, sometimes in obscure ways, to other things that have crossed my radar.
This helps me come up with a wider variety of ideas for how to solve problems in front of me, or new connections to draw on or people to contact for feedback.
I don't care about any one topic enough to devote the necessary time to writing a book about it, but that doesn't mean the system as a whole doesn't provide me a whole lot of value.
Maybe this is just a misunderstanding between the specialist mind and generalist minds. The variety of things I can speak about and connect together intelligently is the value I bring to a company or a conversation, not the extraordinary depth I can go to on any one individual topic. I suspect there are a lot more generalists like me using PKM software like Obsidian than there are specialists.
Same. The more busy and more I have to multi-task and/or manage multiple long-running threads, the more it helps.
Here's a real example: Just this morning I was setting up my new 13th gen framework laptop (it's amazing btw, thank you to framework for making Fedora such a great experience on it!), and I hit Ctrl+r in my terminal to find a previous command. I was surprised to see the standard bash handler instead of the fancy terminal history tool that I installed on my previous laptop. Using my notes I was able to quickly find that the tool is "atuin" and I was able to see exactly what commands I ran to set it up back in the day. This is a tool that doesn't have a great installation story for Fedora. I ended up building rom source and installing, and I'm not a rust person so I would have to look that all up had it not been in my notes. I didn't have time for a long distraction, and my notes saved me on that. It probably adds a 10% to 20% overhead of effort to the original task, but then saves me time in the future.
I have also benefitted greatly from numerous notes on customers/clients that I can pull up and see quickly what the last thing I did/said to them was. After months of not talking to them, it's very easy to forget or blend their details into other customers. The notes can be life savers.
There have also been times when I needed to do some technical task and I remembered having done it years earlier. Finding those notes can be an incredible time saver, especially when it skips me past the first couple hours of research!
What do you think you’d find if you took a similar poll of people who have taken notes on a piece of paper? Have most of them published a book?
My Obsidian vault is full of things like lists of hiking trails I want to check out, information on workshop dust collection, and notes on car shopping. Why would you expect that I’m trying to write a book about it?
To be fair, a lot of people get marketed a "Zettelkasten" because the creator wrote lots and lots of books, and this was seen as proof that the system works. OP didn't pull that out of his ass
To be fair, a lot of people write notes for the purpose of writing notes. Yes he did pull it out of his ass for a very, very tired critique of people who are into note-taking.
I'm not disagreeing with people who like taking notes. I use Obsidian myself (and I'm not weirdly triggered by this comment either). But watch any marketing video for Roam Research or anything adjacent to that and you will usually see people talking about Zettelkasten. In fact, I've seen lots of Obsidian users flat out say you're not actually building a Zettelkasten unless you're outputting original content.
It's not controversial to say Obsidian tool tweaking can be fun and productive, but could also tap into the exact wrong parts of peoples OCD brain.
No reason to be hostile for an observation of a community, especially as low stakes as "notetakers." I don't think they have a monopoly on taking notes?
The knowledge product of my notebook is the notebook. I use it to look up things that I wrote down previously. I also use the process of writing things down in it to guide my thought process.
No, they have not. There are likely far more people taking notes on paper, than there are people who are using Obsidian or similar. Especially when we are not just looking at the present world.
Maybe procrastination isn’t the right characterization of note-taking.
For me, Obsidian is a place to dump thoughts, keep ideas for later, and a scratchpad. It lets me clear my mind of all of the random things that pop up so I can focus more on the tasks at hand. It might sound silly but writing out all the things I’ve been thinking about does wonders for freeing up mental bandwidth, which in my experience is critical for being productive — it’s a lot harder to maintain focus when you’ve got a bunch of different thoughts vying for processing power.
I might not revisit all of my notes, but that’s fine. They’re there when/if I decide to turn them into projects.
I don’t go too far on the organizational or bells and whistles aspects though, the extent of that is folders and the odd tag here and there, because neither really matters much so long as I can find my writings easily.
> It lets me clear my mind of all of the random things that pop up so I can focus more on the tasks at hand.
I think this is key here. It's the same for me. If I don't dump my thoughts int o an organized form they will nag me. When I write them down (and about most of them, I forget or delete later), it allows me to work on the task at hand. If I don't, I end up thinking about all the avenues of exploration of those ideas, todos, etc...
It's akin to how instead of keeping those thoughts in RAM I put them in my SSD. RAM is just for what's happening now.
Yep. It’s an interesting effect. I think half the reason things get stuck in my head like that is because they’re interesting and I don’t want to forget them, so my mind keeps wandering its way back to them. “Hey, what about that fun idea?”
By writing them down I no longer have to worry about them being forgotten since I can always scan over my notes when I’ve got spare mental bandwidth to work with, which stops my mind from wandering.
> I ran a poll recently in a PKM community of 17,000 members asking who has written a book—or created some other knowledge product like a course—using their tool (Obsidian, Zettelkasten, LogSeq, etc.).
That's a very limited choice of options. Or poor phrasing.
> I received two responses of people who actually produced something.
So the others ignored it?
> The vast majority, it seems, are professional note-taking junkies.
I'm not sure if this is poorly phrased or an insult. And what does professional mean? Most of what I manage with Obsidian are private data, nothing work-related.
> People in the Obsidian forum spend their lives fooling around with metadata conventions and "tagging" and "wikilinks"
That's the point of a forum. Talking. Fooling around. How many will you see there talking about the boring stuff? How they use Obsidian for managing contacts, their mealplans, the other boring notes. Probably not many. You will also see the small number of shining characters and fancy solutions, but not much about casual thing people also do.
A "PKM" (personal knowledge management i am assuming) community seems self-selecting for the kind of result you got.
I would do the opposite -- talk to people who clearly have a need for corralling large amounts of information (authors, phd students), and take a a look at what tools they used. It might not be Obsidian or LogSeq specifically, but I'm sure they have some very specific system that works for them... even if its a just a bunch of google docs.
Hey buddy unless you are publishing “Specific Knowledge” (shout out lord Naval for some reason), you have no business writing shit down in a way that you might be able to retrieve it in the future.
You must write on napkins and throw it in the trash or else you are a tryhard pseudo-productivity junkie.
I saw this YouTube video about some historical document from the middle ages (maybe the dark ages?). It was a set of journals/diaries written by a pretty normal guy who lived during the reformation. At first he was documenting the social changes that were going on but pretty soon his journal became a hodgepodge of personal anecdotes, descriptions of his fellow towns folks, gossip and rumors, etc.
One thing that was interesting to me was that he kept a list of amusing anecdotes. The guy was trying to move up in life, so he was doing his best to network with the wealthy elite of his town. He had a personal database of jokes and amusing stories that he could bring up, I guess hoping to gain favor or friendship with the right people.
I've thought about this kind of activity a lot. Not all writing is meant to be for distribution. This guy wasn't writing to compile a tell-all exposé of his tiny provincial town. He was writing entirely for his own selfish benefit.
As curious as it may sound, I can totally understand wanting to hook up an AI to this kind of personal database. Something to make my anecdotes a bit more funny. Or to connect rumors in a way to give me the best gossip.
It reminds me of how VIP type people often have some intern or research assistant who feeds them personal details of the people they are going to meet, so the VIP can warmly ask "How is your daughter Sally?" when shaking hands with someone who is actually a stranger to them.
Not all knowledge is a product. If you see knowledge as a service then these kind of tools make a bit more sense.
How many people of those 17,000 members answered "No" on your poll, to have the denominator? Typically less than 1% of readers actively engage in the communities, or so I have read here in HN. Without a more specific denominator 2 out of 17,000 is the number of people that read you, cared to answer you, self-identified with what you asked specifically, AND "actually produced something".
Note: The requirement wasn't just a book. It was any "published knowledge product"
Frankly, I could do with far fewer "published knowledge products" doing the rounds, and I'm glad that most users are using it as intended, not to get some absurd "published writer" badge to flash to the easily impressed.
We use Obsidian extensively in my company. And are sharing our notes as a graph of decentralized vaults, managed by Github repos and a bunch of synchronization scripts.
That is an experience of collective intelligence that is going super well.
(having access to other people notes in a unified search engine is SUPER nuts!)
Would love to hear more about this -- it's basically the use case that I want to have, that for whatever reason nobody has built. Have you written anything about how you (or someone) hacked this together?
You seem to conflate publishing a book with some kind of legitimacy.
And also determining that if you can’t see value in “note taking”, there is none.
The piece your analysis grossly overlooks is the ability to handle many more things at once using a pkm as second brain.
It’s unfortunate you may not have enough experience with GTD and what it has evolved into.
If you approached this post again with an open mind and heart and said you expected a lot of authors and instead people seem to manage knowledge .. why, and how are people using it for value.. it might be a conversation.
It is entirely possible to publish knowledge products at any time.
In the working world they might include meeting agendas, notes, okr reports, emails and updates to projects.
All can be both specific and esoteric knowledge but many orders of magnitude better organized than their peers.
> Now we have this... ODIN—a way to outsource your intellectual note-taking procrastination to AI.
I'm not sure but it sounds like you're scoffing at that. To me it sounds like the solution to people spending too much time tagging and linking their notes.
I mean...I use Obsidian daily to take notes for my own reference for work every day. It's also typically the place I write blog posts before I publish them to various sites.
I feel like you're giving a very specific use case for production to a tool that isn't really geared for that thing. If I was going to write a book, and I may one day, I don't know whether Obsidian is the tool I'd use or if I'd be better off using tools that are designed for it?
I think the key point here is that for the vast majority of knowledge workers their knowledge work isn't really supposed to result in "published knowledge product" ever, and lack of such a product doesn't imply that they're ineffective since they can be wildly successful at their goals anyway, since why would their goals include producing such a product?
IMHO people taking notes for personal reasons (or building personal knowledge bases just as external memory for their personal expertise) far outnumber people who do that with the intent to compile those notes in some knowledge product for others.
Sure, some people take notes for a book or build a knowledge base that they'll summarize for others in a course or essay(s). But people with such intent are few, so these aren't the central applications of such tools, the stereotypical knowledge workers - like lawyers, doctors, engineers - all mostly apply their knowledge (including digital notes) not to produce or publish something but rather to solve a problem or provide an informed answer, and equating all this "non-producing" knowledge work to intellectual procrastination is quite insulting.
How many people who’ve bought a paper notebook and pen have published same..?
I use Obsidian with a partner to organize an archive that’s used to publish a website, a substack and a podcast. I am familiar with the YouTube obsidian note taking subculture and it’s pretty mega, but online-everything is a poor measure of the real thing in life. Just as Twitter isn’t reality, etc etc….
I’ve written several books using Foam and VScode and I avoid those communities like the plague precisely because they love the tool more than the problems it solves.
I’ve also published (and maintain) several websites using special tags and Hugo tools that compile to HTML markup complete with the requisite hyperlinks and attachments.
I don’t like Obsidian much, personally. I love to customize my tools just enough to get them out of the way.
I use logseq daily to keep track of what I do in my job as a SWE. Having this structured archive is invaluable. I don't understand why you think that note-taking is only justified if you want to create some kind of product - that's a very weird take in my opinion.
I don’t hang out in any community like that, but I use Logseq and Emacs org mode to organize my work at two funded startups, plus occasional consulting to other businesses.
Among other things, I use them for developing design documents, both for my own use and for wider distribution. Often I’ll do the initial work in one and then convert to a pdf, word or google doc, or wiki pages for consumption by others.
I also use them just to track work that I’ve done, which helps a lot with context switching between projects.
I used to just use mostly plain text files to do this, but these tools provide a lot of additional features that make it easier to create and manage useful notes.
I use obsidian for ttrpg world building so I can jump around via links when the party encounters a particular area (helps prevent on-the-rails campaigns.)
Your definition of what "actually matters" seems to be different than mine.
I did this for a while. I think it was a kind of psychological displacement behavior - when I felt a lack of control over my life. A bit like playing animal crossing.
At some point I switched to treating notes as a pipeline - that is, if theres nothing coming out the other end (e.g. a document, a checklist I actually follow, an email, a reminder, a blog post, a jira ticket, etc.) then the activity is pointless.
Doing this meant it actually does bring value now.
LLMs seem like a singularly pointless addition in that respect, though.
I really like your approach of treating notes like a pipeline. I keep several lists and I noticed the only useful ones are those where I regularly cross item off and add new items. All other lists end up being cemeteries for ideas
I had the same impression. They constantly tweak the tools instead of just accepting for what it is and taking their notes/writing their documents. I'd argue if you care so much about note taking software it would be a better use of time to develop your own tool from scratch. At least you would learn something useful and get some experience
I love the idea of building a bespoke notes app for myself, but then again if I had the time and energy I’d probably build my own everything simply because it’s interesting and it feels like there’s unharvested low-hanging fruit in terms of UX improvements across just about all software categories.
Until then though, I’ll be keeping the tinkering to a minimum. Honestly speaking I could probably get by just fine with Sublime Text, a folder full of markdown files, and Syncthing… the main attractions of Obsidian, etc are little QoL features like separate fonts for prose and code.
I think you described the problem very well: the premise behind PKM/note taking is to boost productivity. If you assume this to be true, the only way to be productive is to stop tweaking endlessly and accept the limitations of your tooling
I made the same conclusion and started making a tool on my own from scratch! Turned out it did take much less effort to build something you are happy with than tweaking existing tools.
PWA with Rails/React, editor is Lexical (because why markdown when you can have note looks pretty), hosted on a machine at home that I connect via tailscale.
I would think so too... and even if it doesn't fit you perfectly at least you learn a lot on the way. If you just play with plugins and tweak existing tools, I believe you won't learn anything of substance
> I received two responses of people who actually produced something. The vast majority, it seems, are professional note-taking junkies.
Is external visibility of some output or work product the sole marker of true utility of these tools if one is to avoid the judgement of intellectual procrastination? I’d rather think that’s not the case.
This, so much this. On Twitter, I asked how many people have published a blogpost or anything worth mentioning with obsidian. Turns out my network had 200+ Obsidian users and none of them published anything.
I know the sample size is small but I got similar response with Notion 2 years ago. I use Apple Notes personal note taking and plain markdown with an SSG for publishing blog posts and work. No books yet but I have published over 150+ posts in the past 3 years:
