[HN Gopher] Launch HN: Hyprnote (YC S25) - An open-source AI mee...
___________________________________________________________________
Launch HN: Hyprnote (YC S25) - An open-source AI meeting notetaker
Hi HN! We're Yujong, John, Duck, and Sung from Hyprnote
(https://hyprnote.com). We're building an open-source, privacy-
first AI note-taking app that runs fully on-device. Think of it as
an open-source Granola. No Zoom bots, no cloud APIs, no data ever
leaves your machine. Source code:
https://github.com/fastrepl/hyprnote Demo video:
https://hyprnote.com/demo We built Hyprnote because some of our
friends told us that their companies banned certain meeting
notetakers due to data concerns, or they simply felt uncomfortable
sending data to unknown servers. So they went back to manual note-
taking - losing focus during meetings and wasting time afterward.
We asked: could we build something just as useful, but completely
local? Hyprnote is a desktop app that transcribes and summarizes
meetings on-device. It captures both your mic input and system
audio, so you don't need to invite bots. It generates a summary
based on the notes you take. Everything runs on local AI models by
default, using Whisper and HyprLLM. HyprLLM is our proof-of-concept
model fine-tuned from Qwen3 1.7B. We learned that summarizing
meetings is a very nuanced task and that a model's raw intelligence
(or weight) doesn't matter THAT much. We'll release more details on
evaluation and training once we finish the 2nd iteration of the
model (still not that good we can make it a lot better). Whisper
inference:
https://github.com/fastrepl/hyprnote/blob/main/crates/whispe...
AEC inference:
https://github.com/fastrepl/hyprnote/blob/main/crates/aec/sr...
LLM inference:
https://github.com/fastrepl/hyprnote/blob/main/crates/llama/... We
also learned that for some folks, having full data controllability
was as important as privacy. So we support custom endpoints,
allowing users to bring in their company's internal LLM. For teams
that need integrations, collaboration, or admin controls, we're
working on an optional server component that can be self-hosted.
Lastly, we're exploring ways to make Hyprnote work like VSCode, so
you can install extensions and build your own workflows around your
meetings. We believe privacy-first tools, powered by local models,
are going to unlock the next wave of real-world AI apps. We're
here and looking forward to your comments!
Author : yujonglee
Score : 125 points
Date : 2025-07-29 16:24 UTC (6 hours ago)
| swyx wrote:
| congrats, app looks gorgeous. def a good tauri codebase to study
| ( been using https://deepwiki.com/fastrepl/hyprnote)
|
| any interest in the Cluely-style live conversation help/overlay?
| johntopia wrote:
| thanks! we're focusing on local-first at the moment which makes
| real-time assist a bit challenging. but we definitely have
| something similar on our mind - for example, a live summary of
| what's been going on during the past 5 mins. planning to
| support this via extension in the future!
| yunohn wrote:
| Super cool, congrats on the launch - will be trying this soon! I
| noticed it's using Tauri - what are your main takeaways from
| building a local inference desktop app with it?
| yujonglee wrote:
| Thanks. I learned that running a server on the Rust side and
| calling it from a TypeScript frontend is a good approach. For
| example, we run an OpenAI-compatible server using a Tauri
| plugin (https://github.com/fastrepl/hyprnote/tree/main/plugins/
| local...) and call it using the Vercel AI SDK.
| yunohn wrote:
| I've been thinking about ways to reuse Vercel's AI SDK, so
| this is a great one - thanks for sharing!
| yujonglee wrote:
| Also you might find this interesting:
|
| https://github.com/fastrepl/hyprnote/blob/main/packages/uti
| l....
| yunohn wrote:
| Super neat! You've made an impressive amount of cool
| specialized crates - have you considered making them
| generally usable to the wider community and licensing
| them under LGPL/MIT instead of GPL?
| yujonglee wrote:
| we def considered it. our line of thinking is start with
| more restrictive license, and later switch to MIT or
| something once we figure things out :)
| ashishact wrote:
| I wanted to build this for myself. Could never figure out how
| to get audio output from Mac. Tried almost all audio loopback
| driver (Blackhole, Soundflower ...). There was problem
| everywhere wrt security.
|
| Even tried making a teams meeting bot. But Teams doesn't give
| live audio to developer unless you are a special partner.
|
| Glad you made this. Will play around
| yujonglee wrote:
| Great! We use AudioTap api
| johntopia wrote:
| great to see that you like it :)
| nkotov wrote:
| Really cool - how does it compare to Granola outside of the OSS
| part?
| yujonglee wrote:
| Local-first, controllability(custom endpoint part), and
| eventually extensibility(VSCode part of the post)
|
| We're putting a lot of effort into making it run smoothly on
| local machines. There are no signups, and the app works without
| any internet connection after downloading models.
| ashishact wrote:
| One of the things I would want to do is - As the meeting is
| going on - I would like to ask a LLM what questions I could
| ask at that point in time. Especially if it's a subject I am
| not expert in.
|
| Would I be able to create an extension that could do this?
| johntopia wrote:
| you can definitely do that in the future. but we had that
| on our mind as well from multiple requests - planning to
| add "eli5 - explain like i'm five" and "mmss - make me
| sound smart" ;) (edit: grammar fix)
| quesera wrote:
| Wow, does anything like this exist in current commercial
| tools?
|
| ELI5 sounds useful.
|
| MMSS sounds terrifying though, honestly.
| johntopia wrote:
| i think there are tools like cluely - where they propose
| to "cheat" on everything in real-time. or just wearables
| like waves that shows ar displays with real-time assist.
| (i've never used both of them before, but i understood
| their products like this) so proactive ai agents are
| somewhat becoming a thing I guess. but it all boils down
| to privacy for us.
|
| mmss was something that a lot of users suggested - they
| wanted to be saved from public humiliation
| theodorewiles wrote:
| Looks really cool - I noticed Enterprise has smart consent
| management?
|
| The thing I think some enterprise customers are worried about in
| this space is that in many jurisdictions you legally need to
| disclose recording - having a bot join the call can do that
| disclosure - but users hate the bot and it takes up too much
| visibility on many of these calls.
|
| Would love to learn more about your approach there
| johntopia wrote:
| yes, we're rolling out flexible consent options based on legal
| needs - like chat messages, silent bots, blinking backgrounds,
| or consent links before/during meetings. but still figuring out
| if there's a more elegant way to do this. would love to hear
| your take as well.
| theodorewiles wrote:
| Please shoot me a note - I'm trying to figure this out for my
| enterprise now, would love to figure out a way to get you in
| / trial it out.
| johntopia wrote:
| can i send you a follow-up to the email that's on your
| profile?
| theodorewiles wrote:
| yes
| yonl wrote:
| Congrats on the launch. I never understood why an AI meeting
| notetaker needed sota LLMs and subscriptions (talking about
| literally all the other notetakers) - thanks for making it local
| first. I use a locally patched up whisperx + qwen3:1.7 + nomic
| embed (ofcourse with a swift script that picks up the audio
| buffer from microphone) and it works just fine. Rarely i create
| next steps / sop from the transcript - i use gemini 2.5 and
| export it as pdf. I'll give Hyprnote a try soon.
|
| I hope, since it's opensource, you are thinking about exposing
| api / hooks for downstream tasks.
| yujonglee wrote:
| What kind of API/Hooks you expect us to expose? We are down to
| do that.
| satvikpendem wrote:
| Can you share the Swift script? I was thinking of doing
| something similar but was banging my head against the audio
| side of macOS.
| marcofiset wrote:
| The only issue I have with those tools, and I have not seen a
| single one even acknowledge this, is that it becomes completely
| useless when holding meetings in a hybrid fashion where some
| people are remote and others are in the office with a shared mic.
|
| Almost all of our meetings are hybrid in this way, and it's a
| real pain having almost half of the meeting be identified as a
| single individual talking because the mic is hooked up to their
| machine.
|
| It's a total dealbreaker for us, and we won't use such tools
| until that problem is solved.
| dkdcio wrote:
| I think if you put N-1 mics in the room (where N is the number
| of people) you could easily identify all individuals...
| yujonglee wrote:
| It can be solved with speaker segmentation/embedding models,
| although it is not perfect. One thing we do with Hyprnote is
| that we have a Descript-like transcript editor that allows you
| to easily edit/assign speakers. Once we integrate a speaker
| diarization model with that, I think we'll be in good shape.
|
| If you are interested, you can join our Discord and follow
| updates. :) https://hyprnote.com/discord
| apwell23 wrote:
| our conference rooms even have some sort of rotating camera
| contraption that automatically focus on the person speaking
| nashashmi wrote:
| you might need an AI for in-person meeting first. Such tools
| are available to doctors who see patients. The note taking is
| great but I think it is skewed towards one-person summary where
| the name of the patient remains unknown. I wonder if the same
| tool can take notes if two patients are in the room and
| distinguish between each one.
|
| The second tool is likely hardware limitation. A multi-cam-mic
| with beam forming capability to deconstruct overlapping sounds.
| johntopia wrote:
| hyprnote can be used for in-person meetings as well! we have
| doctors like ophthalmologists or psychiatrists using it right
| now. and yes - definitely going to be working on speaker
| identification as it crucial.
| monkey26 wrote:
| I recently tried Vibe (https://github.com/thewh1teagle/vibe)
| from a recording of a meeting taken on one side. It was able to
| identify the speakers. As Speaker 1, 2, etc. But still useful
| to see.
| abtinf wrote:
| I forbid this kind of meeting on my teams.
|
| Either everyone is in the same physical room, or everyone is
| remote.
|
| The quality of communication plummets in the hybrid case:
|
| * The physical participants have much higher bandwidth
| communication than those who are remote -- they share private
| expressions and gestures to the detriment of remote.
|
| * The physical participants have massively lower latency
| communications. In all-online meetings, everyone an adjust and
| accommodate the small delays; in hybrid meetings it often locks
| out remote participants who are always just a little behind or
| have less time to respond.
|
| * The audio quality of remote is significantly worse, which I
| have seen result in their comments being treated as leas
| credible.
|
| * Remote participants usually get horrible audio quality from
| those sharing a mic in the room. No one ever acknowledges this,
| but it dramatically impacts ability to communicate.
| ls-a wrote:
| Looks great. From my experience Tauri team has no clue what
| mobile is and they're not interested in fixing mobile issues. I
| can already tell the mobile version will be a disappointment.
| yujonglee wrote:
| We tried Tauri mobile (few months ago) and had the same
| disappointment. We will use RN or Dioxus(to share Rust code)
| for the mobile version. So it will be cool :)
| ls-a wrote:
| I'm glad you figured that out early on. Sounds like mobile is
| going to be great indeed
| toisanji wrote:
| is this a known pattern, I did a basic tauri app, but not
| sure what to do with mobile yet...
| johntopia wrote:
| from our experience, we tried using stackflow on the
| frontend but encountered problems with responsive keyboard
| layouts. thought it was stackflow's problem but soon
| realized that it just wasn't implemented in tauri yet.
|
| ref: https://github.com/daangn/stackflow
| nashashmi wrote:
| I was talking about this a week ago. One person wanted to make a
| pdf tutorial of how to use a software. I asked him to record
| himself in teams and share his screen and have AI take notes. It
| will create a fabulous summary with snapshots of everything he is
| going over.
| b0dhimind wrote:
| Look forward to testing the Windows version. Hope it has ability
| to also upload recordings, etc. Meetily is nice but setup feels
| too convoluted, with a backend and frontend being required to
| separately install...
| johntopia wrote:
| will push harder! hop into our
| discord(https://hyprnote.com/discord) to get the latest updates
| :) you can sign up to the waitlist on our website as well.
| woadwarrior01 wrote:
| Congrats on the launch. Is there a reason why the app isn't
| sandboxed?
| yujonglee wrote:
| What kind of sandboxing you expect? keen to learn more about it
| since we care about security too. (one reason why we use Tauri
| over Electron)
| p2hari wrote:
| I just downloaded on mac M4 pro mini. I installed the apple
| silicon version and try to launch it and it fails. No error
| message or anything. Just the icon keep bouncing on the dock. I
| assumed it needs some privacy and screen recording and audio
| permissions and explicitly gave them, however still just jumps on
| the dock and the app does not open. (OS, mac sequoia 15.5)
| johntopia wrote:
| working on trying to identify the problem! could you come over
| to our discord where we could better support you?
| https://hyprnote.com/discord
| yujonglee wrote:
| That is very strange. Can you launch it from the command line
| and share what you got?
|
| /Applications/Hyprnote.app/Contents/MacOS/Hyprnote
| yujonglee wrote:
| Seems like
|
| https://github.com/fastrepl/hyprnote/blob/d0cb0122556da5f517...
|
| this is invalid on Mac mini. Should be fixed today.
| kocial wrote:
| Nicely done, I or someone can push the translation option too.
| Well done.
| johntopia wrote:
| what language do you have in mind? would love to know!
| turnsout wrote:
| Congrats! I'm currently a Granola user, and wanted to build this
| myself a while back. But I probably wouldn't have gone as far as
| fine-tuning a small model for meeting summarization. Can't wait
| to try it out!
| yujonglee wrote:
| Super! let us know how it goes! (we have discord channel too)
| turnsout wrote:
| Installation and onboarding was nice & smooth!
|
| A few random bits of realtime feedback:
|
| You have an icon with the Finder face labeled "Open Finder
| view." I would expect this to open the app's data folder in
| the macOS Finder. Instead, it opens an accessory window with
| some helpful views such as calendar view. I'd encourage you
| to find another name for that window, because it's too
| confusing to call it "Finder" (especially with the icon).
|
| I'd also add a menu item for Settings (and Command-comma
| shortcut) in the Application menu.
|
| You also need a dark mode at some point.
|
| Finally, I'm not sure where note files end up. Seeing that
| there's an Obsidian integration, I would love an option to
| save notes in Markdown format into a folder of my choice. I'm
| an iA Writer user, and would love to have meeting notes go
| directly into my existing notes folder.
|
| I'll let you know how the actual functionality is working for
| me after my next few meetings!
| johntopia wrote:
| haha we couldn't find a better icon for the "Finder" view
| so we just went with the classic one. but i guess it's
| confusing - noted.
|
| we do have settings shortcut already! be sure to test it
| out :)
|
| dark mode - noted as well.
|
| we save our notes in db.sqlite that can be found in:
| ~/Library/Application\ Support/com.hyprnote.stable
|
| this decision was made because we have three documents -
| raw note, enhanced note, and transcript - assigned to a
| meeting note.
|
| would love to create an iA integration for you - or just a
| simple way to export MD for the time being
|
| join our discord for more updates!
| https://hyprnote.com/discord
| teiferer wrote:
| Nice!
|
| Would be great if you could include in your launch message how
| you plan to monetize this. Everybody likes open source software
| and local-first is excellent too, but if you mention YC too then
| everybody also knows that there is no free lunch, so what's
| coming down the line would be good to know before deciding
| whether to give it a shot or just move on.
| yujonglee wrote:
| For individuals:
|
| We have a Pro license implemented in our app. Some non-
| essential features like custom templates or multi-turn chat are
| gated behind a paid license. (A custom STT model will also be
| included soon.) There's still no sign-up required. We use
| keygen.sh to generate offline-verifiable license keys.
| Currently, it's priced at $179/year.
|
| For business:
|
| If they want to self-host some kind of admin server with
| integrations, access control, and SSO, we plan to sell a
| business license.
| rushingcreek wrote:
| Congrats on the launch! I'm very bullish on how powerful
| <10B-param models are becoming, so the on-device angle is cool
| (and great for your bottom line too, as it's cheaper for you to
| run).
|
| Something that I think is interesting about AI note taking
| products is focus. How does it choose what's important vs what
| isn't? The better it is at distinguishing the signal from the
| noise, the more powerful it is. I wonder if there is an in-
| context learning angle here where you can update the model
| weights (either directly or via LoRA) as you get to know the user
| better. And, of course, everything stays private and on-device.
| yujonglee wrote:
| > How does it choose what's important vs what isn't?
|
| The idea of Hyprnote is that you write chicken-scratch-raw note
| during the meeting(what you think is important), and AI enhance
| based on it.
|
| On-device learning is interesting too. For example, Gboard:
| https://arxiv.org/abs/2305.18465
|
| And yes - we are open to this too
| manveerc wrote:
| Congratulations! Is there a mobile version as well, especially
| for Android?
| johntopia wrote:
| have it planned for the 4th quarter!
| thephotonsphere wrote:
| Looks promising, but "Linux maybe"? Signing off.
| johntopia wrote:
| it was a joke! we are strongly considering to get it done after
| windows(shipping in aug)
| tomr75 wrote:
| why use whisper over parakeet? how will you monetise?
| yujonglee wrote:
| Whisper is more lightweight and smaller. We will support
| Parakeet in the near future too.
|
| Monetization:
|
| For individuals: We have a Pro license implemented in our app.
| Some non-essential features like custom templates or multi-turn
| chat are gated behind a paid license. (A custom STT model will
| also be included soon.) There's still no sign-up required. We
| use keygen.sh to generate offline-verifiable license keys.
| Currently, it's priced at $179/year.
|
| For business: If they want to self-host some kind of admin
| server with integrations, access control, and SSO, we plan to
| sell a business license.
| pokechamp wrote:
| another free tier (but not opensource) recording tool Ive been
| using is MacWhisper. Does this and more all locally too. Will try
| hyprnote out because its neat to do the transcription in real
| time and its note taking purposes
|
| https://goodsnooze.gumroad.com/l/macwhisper
| yujonglee wrote:
| we will support even faster realtime transcription in near
| future. (within few weeks)
| satvikpendem wrote:
| What model? All the realtime transcription services I've seen
| are Whisper wrappers or custom closed source ones.
| yujonglee wrote:
| It's custom model. (whisper variant)
| satvikpendem wrote:
| Makes sense. How well do you expect Hyprnote to work on
| mobile? I found that phones in general are still pretty
| weak at AI inference on-device still.
| yujonglee wrote:
| I think it will work pretty well considering how rapid it
| moves. (See gemma3n, Cactus etc)
| kpen11 wrote:
| This is really cool! I've been using Obsidian more and more as a
| second brain and getting data in has consistently been the point
| of failure, so I've been wanting something just like this.
| Specifically something that runs locally and offline.
|
| Is the future goal of Hyprnote specifically meeting notes and
| leaning into features around meeting notes, or more general note
| taking and recall features?
| yujonglee wrote:
| At least for near future, we'll focusing on meeting notepad
| side of a thing.
|
| We actually have "export to Obsidian". I think you can pair
| Hyprnote nicely with Obsidian.
|
| Screenshot: https://github.com/user-
| attachments/assets/5149b68d-486c-4bd...
|
| You need this plugin installed in Obsidian first:
| https://github.com/coddingtonbear/obsidian-local-rest-api
|
| Obsidian export code 1:
|
| https://github.com/fastrepl/hyprnote/blob/d0cb0122556da5f517...
|
| Obsidian export code 2:
|
| https://github.com/fastrepl/hyprnote/tree/main/plugins/obsid...
| ljosa wrote:
| Why in the world is there _background music_ when I start the
| app?!
| yujonglee wrote:
| We thought it'll be cool :) sorry if that disturbs you.
| ljosa wrote:
| Glad you're having fun, but it had the "website with
| autoplay" vibe.
| yujonglee wrote:
| It should be played only during onboarding. No music while
| using the app
___________________________________________________________________
(page generated 2025-07-29 23:00 UTC)