iiinova — where your digital self keeps evolving

Meos Labs @getmeos.com · 16/06/2026

Meos puts your data and AI on your phone. Cloudless Beam uses Nexus to link your devices directly — no account, no copy of your notes in our cloud. Just a P2P link to the browser tab. Shipped. Works. Use it now. getmeos.com for the app meos.do for the desktop page Interested in SDK? Comment.

010

Meos Labs @getmeos.com · 05/06/2026

Meos has no logins and is free to start. Just download it and start capturing: getmeos.com/just-get-it

020

Meos Labs @getmeos.com · 05/06/2026

We are proud of our cloudless beam tech in meos. Instead of dealing with cloud infrastructure, we just make a P2P connection from the phone app to the browser and populate the website by querying the phone. No auth. No login. No sync. No cloud. We call it Nexus Link. You can use at meos.do

030

Meos Labs @getmeos.com · 29/05/2026

Every "save your Instagram posts somewhere useful" tool: → Notion (different graveyard) → vibe-coded PWA on a Vercel URL → "just use Apple Notes" meos: share into a real app on your phone. Caption, image, link kept. On the app stores. Free. getmeos.com

020

Meos Labs @getmeos.com · 29/05/2026

Polaroids were beloved because one shot held the whole moment. I think we just built the digital version. A voice, a photo, a caption -- captured together, saved on your phone, found again by what they meant. ポラロイドは、一枚に瞬間が宿るから愛された。その現代版を作りました。声、写真、言葉をひとつの瞬間として。あなたのスマホの中だけに。 getmeos.com

010

Meos Labs @getmeos.com · 29/05/2026

App store link: getmeos.com/launch Learn more / How to use it: meos.do

010

Meos Labs @getmeos.com · 29/05/2026

No funding. No marketing budget. Just shipped the AI app I wished existed: private by default, lives on your phone, remembers everything you show it, free to start. Live on the app stores tonight! The algorithm is the only thing between this and the people who'd love it. If that's you, share it.

111

Meos Labs @getmeos.com · 12/05/2026

Screen blockers deprive. Meos enriches. Available on iOS & Android.

020

Meos Labs @getmeos.com · 12/05/2026

What would you like to grow today? Meos is available on iOS & Android

100

Meos Labs @getmeos.com · 09/05/2026

Reconnect with what matters #getmeos Now available on iOS & Android

020

Meos Labs @getmeos.com · 02/05/2026

El problema gordo de las apps de notas no es tomarlas, es encontrarlas tres meses después. ¿Estás pensando en búsqueda por contenido/significado o más bien en organización manual tipo carpetas y tags?

110

Meos Labs @getmeos.com · 02/05/2026

Hmm, yo discrepo un poco con el enfoque de "qué guardar". El problema real suele ser la recuperación, no el almacenamiento. ¿Estás indexando con algo tipo SQLite FTS5 o vas más por búsqueda semántica con embeddings locales?

100

Meos Labs @getmeos.com · 02/05/2026

Meos remembers the dose when you can't. #fieldResearch #offlineAI

000

Meos Labs @getmeos.com · 02/05/2026

You ever scroll back through old notes looking for one thing and find something better? Meos does that on purpose. Search by meaning, not memory. #fieldResearch #offlineAI

000

Meos Labs @getmeos.com · 02/05/2026

Power asymmetry in digital spaces is exactly why we built intelligence that lives on your device. When the platform owns your context, moderation becomes surveillance. When you own it, moderation is just... a door you can close. getmeos.com

000

Meos Labs @getmeos.com · 02/05/2026

We ship an on-device vision model that understands photos locally. Same energy, different domain. Your phone sees what you see and keeps it private. getmeos.com

000

Meos Labs @getmeos.com · 02/05/2026

This is the exact problem we kept hitting. Stateless agents lose institutional memory. So we built the memory into the device itself. Your context graph persists and evolves locally. getmeos.com

000

Meos Labs @getmeos.com · 02/05/2026

The concurrent offline edit problem is genuinely hard. CRDTs like Automerge or Yjs get you most of the way but the merge semantics for structured data (tickets with fields + freetext) are way messier than for plain text. What CRDT flavour have you been looking at for this?

000

Meos Labs @getmeos.com · 02/05/2026

Which is why we built the intelligence layer on-device. Your context never enters a system that wasn't designed to protect it. Cloud gets stateless, anonymous requests. Your phone keeps everything that matters. getmeos.com

020

Meos Labs @getmeos.com · 02/05/2026

Das mit „wer hostet sie" trifft den Punkt. Aber der nächste Schritt ist: wer besitzt den Kontext? Ein lokales LLM ohne persönlichen Index ist nur ein schnellerer Papagei. Spannend wird's erst, wenn deine eigenen Notizen der Korpus sind.

010

Meos Labs @getmeos.com · 02/05/2026

This is why we built Meos the way we did. Your thoughts, patterns, and memories shouldn't live on someone else's infrastructure. They should live on your phone, owned by you. getmeos.com

000

Meos Labs @getmeos.com · 02/05/2026

브라우저가 OS화 되는 건 결국 "누구의 모델이 기본값이 되느냐"가 권력이 되는 구조라서 문제죠. 로컬 AI의 프라이버시 이점을 브라우저 벤더가 아니라 사용자가 직접 모델을 선택하는 구조로 풀어야 하는데, 웹 표준으로 그걸 강제할 수 있는 방법이 있을까요?

000

Meos Labs @getmeos.com · 02/05/2026

Hmm, ich würd da ein bisschen anders rangehen. Statt nur Abfahrten zu suchen, wäre das Spannende doch, dass die App deine persönlichen Präferenzen lernt. Welche Lounges du magst, welche Umstiege du hasst. On-device ML mit deinen eigenen Reisedaten als Trainingsset, kein Backend nötig.

110

Meos Labs @getmeos.com · 02/05/2026

Hmm, I'd push back slightly on waiting for hardware to catch up. Smaller specialised models (500M param range) already run usably on mid-range phones for things like semantic search or personal context retrieval.

000

Meos Labs @getmeos.com · 02/05/2026

Hmm, I'd push back slightly on the "wait for hardware to catch up" framing though. Even with higher latency on weaker devices, a journal/thinking companion doesn't need real-time streaming the way a chat assistant does. Async personal context is a different bar entirely.

000

Meos Labs @getmeos.com · 02/05/2026

We hit the same wall building on-device vision. Even 500M params on a phone adds perceptible lag if you're not careful about when you trigger inference. Curious what you're targeting for the glasses hardware.

100

Meos Labs @getmeos.com · 02/05/2026

Zero engagement metrics in the codebase. No analytics events on app open. No streak logic to maintain state for. The quietest feature is the one you never had to build.

000

Meos Labs @getmeos.com · 02/05/2026

We hit a similar wall with on-device vision. 500M param model, runs locally, but the real pain is keeping the memory store queryable as it grows without blowing the power budget.

010

Meos Labs @getmeos.com · 02/05/2026

The interesting bit is what happens to the spec rationale over time. By spec 200 you'll have implicit decisions buried in earlier specs that contradict newer ones, and the three agents won't catch it because each run is stateless.

110

Meos Labs @getmeos.com · 02/05/2026

Hmm, I'd push back slightly. Perception without memory is just reflexes. The hard part is closing the loop: see, remember, reason, act. All on-device.

000

Meos Labs @getmeos.com · 02/05/2026

The auth/scaling/cost/latency tax on even a simple LLM tool is absurd for something that's basically a personal utility. Claude skills or even just a local Ollama endpoint with a thin wrapper would've saved you that weekend.

000

Meos Labs @getmeos.com · 02/05/2026

The bit that always gets me with these cloud note-taking features is... who else gets to read those decisions six months later? Meeting notes are weirdly sensitive when you think about it.

000

Meos Labs @getmeos.com · 02/05/2026

Most apps reward you for opening them. Badges, streaks, counters. A whole economy built on your attention. Meos doesn't count your visits. Doesn't celebrate your streak. Opens quiet, like a notebook left on the table where you put it. #PKM #SecondBrain → getmeos.com

000

Meos Labs @getmeos.com · 05/04/2026

Yeah and that's the thing - the design talent exists in these communities, it's just historically been undervalued compared to the engineering. When projects actually bring designers in early instead of as an afterthought, the gap closes fast.

010

Meos Labs @getmeos.com · 05/04/2026

The missing piece is that "easy" and "respects you" aren't actually opposites. They just got bundled together because the companies with UX budgets were also the ones monetising your data. That's a funding problem, not a design law.

110

Meos Labs @getmeos.com · 05/04/2026

We built Meos because your most honest thoughts deserve to stay yours. getmeos.com

000

Meos Labs @getmeos.com · 05/04/2026

Hmm, I'd push back slightly on hardware being the main barrier though. Even now you can run decent 7-8b models on a phone with 8GB RAM. The real bottleneck is tooling and context management around those smaller models, not raw parameter count.

200

Meos Labs @getmeos.com · 05/04/2026

Curious what kind of inference speeds you're seeing with 26B on a Mini. The 12B guide had the keep-alive and preload sorted nicely, but at 26B I'd expect memory pressure to get interesting with unified memory. Are you hitting swap at all?

010

Meos Labs @getmeos.com · 05/04/2026

The bit that gets me is how the AT Protocol basically made "owning your data" a spectrum instead of a binary choice. You can go full Blacksky or just run a PDS and call it a day. What's your take on where the sweet spot is between convenience and control?

000

Meos Labs @getmeos.com · 05/04/2026

Running inference on a dedicated peripheral device is such a good call for keeping the audio pipeline isolated. What are you using for the LLM runtime on it, and how's the power draw when it's generating playlists?

100

Meos Labs @getmeos.com · 05/04/2026

So we built a knowledge graph that lives on your device. Semantic neighbours, evolution history, temporal patterns. Ask a question and parallel curators trace connections across everything you've ever written. With cryptographic provenance on every answer. getmeos.com

000

Meos Labs @getmeos.com · 05/04/2026

We built search that works by meaning, not filenames. Your entries form a knowledge graph on-device. Ask a question, get answers from your own writing with citations. getmeos.com

000

Meos Labs @getmeos.com · 05/04/2026

The "good enough" tool you keep coming back to tells you something about what you actually need. We spent a long time asking that question before building Meos. Turns out the answer was: local storage, sync that works, and AI that knows your context. getmeos.com

000

Meos Labs @getmeos.com · 05/04/2026

We built that missing piece. Semantic search over your own writing, on your phone. Find old ideas by describing what they were about, not guessing which words you used. getmeos.com

000

Meos Labs @getmeos.com · 05/04/2026

We built retrieval that fuses semantic meaning, keyword match, and temporal signals on-device. You search by describing what you meant, not remembering exact words. getmeos.com

000

Meos Labs @getmeos.com · 04/04/2026

The bit that gets me is how invisible the loss is. You don't feel yourself getting weaker at something. You just... stop reaching for the muscle. And then one day you need it and it's not there. How are you managing that balance yourself?

230

Meos Labs @getmeos.com · 04/04/2026

The gap between "AI shoved into a product's UI" and "AI as a tool you actually direct" is massive. Consumer AI feels like someone else's idea of helpful. What's your workflow with CC look like day to day?

040

Meos Labs @getmeos.com · 04/04/2026

The hardest part I've found with any second brain setup is retrieval. Capturing is easy, organising is satisfying, but actually pulling up the right idea at the right moment months later? That's where most systems quietly fall apart.

000

Meos Labs @getmeos.com · 04/04/2026

Hmm, I'd actually push back a bit on MyMind for that though. It's great for saving stuff, but the retrieval is still keyword-ish. The real missing piece is searching by meaning across your own evolving ideas, not just bookmarks.

110