Asmir

@byjasonz @ItsMatthewAo @BapnaArihant whats your biggest takeaways while building skyglass?

we just gave your computer infinite storage. quickly find and edit terabytes of files, all while using zero disk space. here’s a first look, updates shipping daily.

@Shpigford everybody wants a personal ai that does the work for them. no one thinks of using Ai as a true cofounder that challenges your thinking, keeps you focused on the task that matters, helps curate your knowledge in a structured way etc. built moveros.dev to solve this.

what's the "personal AI" that doesn't require a blood sacrifice or a PhD in quantum physics to use? who's built the "Apple" of personal AI where it Just Works™?

@beffjezos Just use both

In retrospect when the normies started Claudeposting you already knew that was the peak.

Heavily depends on how you use it in the first place. It took months of iteration and using moveros.dev which I use to extract my daily data (sleep, what i ship, what i avoid etc) Then it uses this data and finds patterns about me and uses those to help me understand myself better, questions my thinking, pushes back on when i start doing things that aren't going to push me towards my goals and so much more just wrote a full guide on exactly this, link is in my profile

I’ve talked about this. We’re only going to see this kind of thing unfold with greater intensity, at larger scale, as time goes on.

I understand where you're coming from but it's not the same at all especially due to having access to LLMs now. What matters the most is our core content on obsidian and that's a universal MD format. All of that exists locally, you can add another software like obsidian and connect it to your existing knowledge base. Most of the other softwares you have to export the content and even then it's very finicky. There's a reason why Claude code and obsidian can co exist together whereas something like notion, apple notes or others can't. That difference allows you to then curate your knowledge in a way where both human and LLM have a way to view and interact with it. That's what I have been doing with moveros.dev where I am curating a high quality knowledge repository for any future LLMs that would have higher context windows and ingest all that knowledge at once to help me better utilise and understand it etc.

I want to debunk the claim that I see a lot around here that Obsidian is "just plain text markdown files" which means "you can take them anywhere and open them with any app" That simply isn't true Yes, maybe the raw text of the notes is markdown, but many other parts cannot be moved elsewhere and opened by other apps: 1. The .obsidian/ directory contains your JSON config with plugins, settings, hotkeys, workspace state, link format, attachment paths – those can't be moved elsewhere 2. Plugin state files – Readwise's path-to-ID map, Templater's settings, Tasks plugin's database, Excalidraw's drawing data – even if plugins can be recreated, these settings cannot 3. .canvas files – JSON, not markdown. They reference notes by path and won't survive a move 4. .base files – JSON-based database/views over your notes. Same path-fragility 5. .excalidraw.md files – markdown wrapper around an Excalidraw JSON blob. Looks like markdown, isn't really 6. The link graph itself – backlinks, graph view, "linked mentions" – all computed from filenames and link references. They survive because the references are in the markdown, but they require Obsidian (or an Obsidian-aware tool) to materialize 7. Plugin-managed folders – Readwise output, Web Clipper output, Daily Notes location, Templates folder. Each is a folder whose contents are owned by an external system tracked in plugin state 8. Sync state – Obsidian Sync, iCloud, Dropbox, Google Drive each maintain their own state about what's where and what's been resolved. Move operations interfere with this state 9. Embedded query results – Dataview queries, Tasks queries, Bases queries. The query is in the markdown; the result is computed live and never persisted So technically you CAN move your files elsewhere, but you'd destroy most of what makes them valuable – the graph, the plugin state, the canvases, the embedded queries, the sync state, and any structural intent encoded in folder placement Which means you're just as locked in to Obsidian as any other "proprietary" app, it's just a hidden lock-in that's obscured by inaccurate marketing Saying "Obsidian is just markdown files" is like saying "your house is just bricks" The bricks are real and moveable – but the architecture, plumbing, and wiring aren't bricks, and those are most of what makes the house function

@cto_junior in my head? if it's in your head forget it ever existed, you can't rely on memory for anything important, thats why moveros.dev just takes all the data from my conversations with ai and any tasks i mention get noted down for the future and resurfaced when relevant.

How do you manage multiple tasks in your head while using Codex / Claude Code? What actually helps you stay organized enough to get real leverage out of them?

there needs to be intention with everything we do in life, claude code and other LLMs have made it easy to execute so we think less before doing so this was my biggest problem with AI so thats why now i have a very aligned system (moveros.dev) that takes data from my daily life, all actions i do, every project i work on, what i eat, sleep, how i perform, etc and it creates files within obsidian that are basically my entire conscious life now using those conscious details it extracts what's hidden due to its pattern recognition, and gives the underlying patterns about myself, i have had more self reflection through this then doing any other thing in life everyday it helps me make better decisions and keeps me focused on the singular thing that is going to move the needle for me in my life, it's honestly quite cool.

I'm 41 and feeling this way. I finally hit a wall recently. It isn't as fun to use AI like this. I want deep work and instead I end up juggling 4-5 agents that randomly go sideways on me. It is 100% my eagerness to build fast. I'm forcefully slowing down and reading the code again to get better quality and enjoy the process a bit.

i am also 22 and i had the opposite happen, more clarity, better reasoning, sharper strategy etc the difference is how i have setup claude code in a very particular way. i built moveros.dev which takes my daily data (sleep, what i ship, what i avoid etc) so it uses this data and finds these patterns about me and then uses those to help me understand myself better, questions my thinking, pushes back on when i start doing things that aren't going to push me towards my goals and so much more just wrote a full guide today on exactly this, link is in my profile

@AishwaryaDevv well that does not have to be an issue anymore, thank me later: x.com/asmirkn/status…

Most annoying part of vibe coding? Re-explaining the entire context to your IDE after switching chats

That's why i am currently building a local knowledge base with everything i know about myself and expanding it daily by using moveros.dev, because tomorrow when better and local models come around they will take that data and help me make better decisions, improve my life in terms of health, wealth and relationships etc.

I’m extremely bullish on open-source AI Not to discount frontier labs or closed source solutions But the pace of improvement, community energy, and sheer economic pressure from surging AI demand all point in one direction

@SokeyeA Obsidian 100%, i have my entire AI second brain in there using moveros.dev

What notes app do you prefer and why ? - Apple Notes - Google Keep - Obsidian

@svpino I came to the same conclusion but i dont copy the entire thing, i just run /compact anyway and the entire history gets saved into a md file automatically then subagents review it and pull the most relevant information based on my query, it's a feature in moveros.dev

I'm spending so much time managing context, and I hate it. Here is a tip for you: don't use /compact any more in Claude Code. There's a much better option. /compact takes your entire conversation history in memory and compresses it into a summary. This frees up tokens, but you'll lose a ton of important details (sometimes up to 70% of what matters!). On top of that, the summarized context is still tied to the current session and won't persist beyond it. Here is what you should do instead: 1. Dump the entire conversation history to a markdown file 2. Call /clear to clear the context 3. Start your next prompt by pointing to the markdown file There are several advantages to doing this: 1. You don't lose any valuable information 2. You control what's in the file 3. The context persists beyond the current session In summary, when you hit a context limit, do a *handoff*, not a *cleanup*.

@VictorTaelin brother this is solved easy with hooks + some proper file structuring, i did it with moveros.dev, working with ai is not the same anymore.

seriously, working with AI is MISERABLE for one and only one reason: having to re-explain the same thing "oh yeah this new session obviously doesn't know what proper case trees are, so let me explain it for the 5000th time in my life" I'm tired AGENTS.md doesn't solve this because it is impossible to fit the entire domain knowledge without nuking the context - it would be 1m+ tokens worth RAGs don't solve this, the agent won't search unknown unknowns SKILLs don't solve this unless I keep like a collection of 1750 skills with specific cuts of domain knowledge for each possible subset of my domain that I might need in a given chat, but that's a lot of manual work recursive LLMs or whatever don't solve this for the same reason, you can't dump a domain book and expect the AGENT will magically guess that it is supposed to search for a specific bit knowledge. unknown unknowns fine tuning doesn't solve this (OSS models suck and OpenAI / Anthropic gave up on user fine tuning) I honestly think a good product around fine tuning on your domain would be a major hit and an underdog lab should take this opportunity

I am also 22, honestly i have had the opposite happen, i have more clarity, better reasoning, more strategy etc. It's because how i have setup claude code and all my other ai agents in a very particular way right now i have a very aligned system (moveros.dev) that takes data from my daily life, all actions i do, every project i work on, what i eat, sleep, how i perform, etc and it creates files within obsidian that are basically my entire conscious life now using those conscious details it extracts what's hidden due to its pattern recognition, and give some underlying patterns about myself, i have had more self reflection through this then doing any other thing in life an even better part about this is that because it knows my downsides, it can help me overcome them when i use it on a day to day basis and generally just allow me to perform better in life, it's quite cool

I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless

@milesdeutscher I see so many people waste their time on this when they can simply use moveros.dev which sets up your ai second brain in 15 minutes with all the best practices, then you just use it and it helps you get stuff done. Quite simple!

If you do just ONE thing in AI this week, make it this. It's the highest leverage thing you can do right now. - Set up your Obsidian (takes 5 minutes) - Start populating with personal info (use Claude code to index) Article here for readers, video below for visual people. 🫡

Honestly, this is great info but the sad part is most of the people are going to miss out on having an Ai second brain because there's so much info out there and no proper implementation. That's why I built moveros.dev, it sets up your second brain in 15 minutes and then you just use it to do the work.

@ansubkhan @karpathy or if you just want a working second brain with all the best configurations just use moveros.dev, it will setup your second brain in 15 minutes so you can actually get stuff done.

a lot of you asked for a deeper look at the @karpathy inspired local wiki setup i posted before. here’s the full video of installing and walking through Wiki OS and seeing how it works.

@YashHustle_22 It's 2026 and you're still complaining about this? I solved this 6 months ago using moveros.dev

Most annoying part of vibe coding? Re-explaining the entire context to your IDE after switching chats

@RoundtableSpace 17 minutes lmao??? moveros.dev sets up your second brain with all the best practices in less than 15 minutes. Then you just use it no need to configure anymore.

Obsidian + Claude Code builds a real second brain in 17 minutes. Claude Code reads entire vault, connects notes & builds a knowledge graph of everything you've ever written. Bookmark it. This one actually works.