stfurkan
Re:Ask HN: What are you working on? (September 2026)
on Monday September 14, 2026 @07:28PM (#49705655)
- Muntazam: simple and fully local habit tracker (Android version is coming soon)
Link: https://apps.apple.com/us/app/muntazam-habit-tracker/id68053...
- Carbonless: Calculate your website's carbon emissions
Link: https://carbonless.cc
- Aidekin: An AI assistant that runs inside your visitor’s browser
Link: https://aidekin.com
Re:Ask HN: What are you working on? (August 2026)
on Monday August 10, 2026 @05:38AM (#49241435)
1. bitgpu: Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser.
Repo: https://github.com/stfurkan/bitgpu
Demo: https://stfurkan.github.io/bitgpu/examples/chat.html
2. aidekin: In browser local AI assistant for any website (it uses the bitgpu engine)
Repo: https://github.com/stfurkan/aidekin
Website: https://aidekin.com
3. Carbonless: Calculate and reduce your website's carbon emissions
Website: https://carbonless.cc
Re:Ask HN: What are you working on? (August 2026)
on Sunday August 02, 2026 @06:16PM (#49148988)
I'm currently working on an open-source LLM inference engine [1] for browsers via webGPU. If anyone wants to try or has any suggestions, I'm happy to listen :)
1. https://github.com/stfurkan/bitgpu
Demo: https://stfurkan.github.io/bitgpu/examples/chat.html
2. https://aidekin.com --> this is one of my project that's currently using bitgpu engine
Re:1-Bit LLM in the Browser
on Tuesday July 21, 2026 @02:58AM (#48988986)
Hi again :) I updated the engine and 27B model should work in the demo[1]. We can still consider it as experimental but I am trying to make it better and efficient.
Re:1-Bit LLM in the Browser
on Monday July 20, 2026 @01:20PM (#48981812)
Thank you :) I wanted to create it from zero myself so I can control it better. e.g. I started with ONNX support but now it support gguf models too. It might be a good idea to add some popular connectors in the future. Good luck with your project :)
Re:1-Bit LLM in the Browser
on Monday July 20, 2026 @08:34AM (#48977969)
Hello, I sent you a LinkedIn connection request. We can chat first and schedule a meeting. Thanks
Re:1-Bit LLM in the Browser
on Monday July 20, 2026 @08:33AM (#48977947)
Hi, the engine itself already has tool calling capabilities but if you're asking for the aidekin I didn't add tool calling there on purpose.
It needs webgpu support but I haven't had a chance to test with different devices.
Re:1-Bit LLM in the Browser
on Monday July 20, 2026 @04:48AM (#48975987)
Hi :) There are some smaller embedding and re-ranking models (I am currently using some of them on my aidekin project) but having it like bonsai models will be great to have.
Re:1-Bit LLM in the Browser
on Monday July 20, 2026 @04:44AM (#48975944)
Thank you for trying it :) I just added the 27B support 1 hour ago. Let me check and try to fix it. All other models should work as expected but if you have issues with them too, I can take a look.
Re:1-Bit LLM in the Browser
on Monday July 20, 2026 @04:16AM (#48975698)
I'm currently working on an open-source engine [1] exactly for this purpose. If anyone wants to try or has any suggestions, I'm happy to listen :)
1. https://github.com/stfurkan/bitgpu
2. https://aidekin.com --> this is one of my projects that's currently using bitgpu engine
Re:Speech Recognition and TTS in less than 500kb
on Saturday July 18, 2026 @05:55PM (#48962841)
It looks great, thank you! I'll see if I can use it for my in browser AI assistant project's ( https://aidekin.com ) voice part. It's currently using Nemotron-3.5-ASR and supertonic-3 but overall it requires 1.2gb download.
Re:Ask HN: What Are You Working On? (July 2026)
on Monday July 13, 2026 @08:55AM (#48891961)
aidekin: an open-source, client-side AI assistant you drop onto any website. Your visitors get a private voice and text assistant that runs entirely on their own device via WebGPU
Re:Show HN: I wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the br...
on Tuesday July 07, 2026 @03:08PM (#48822203)
Thank you :) Currently I am not planning to have hosted fallback Q&A but it's a nice idea. It should only download the ~300mb initially once and then use the cached model.
Show HN: I wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the browser
Re:Ask HN: What Are You Working On?
on Monday June 15, 2026 @01:51PM (#48544770)
I see, thanks for the feedback :) It'll be a nice addition to the game.
Re:Ask HN: What are you working on? (June 2026)
on Monday June 15, 2026 @01:50PM (#48544754)
Thank you for the feedback :) Letting players play before signing up might not be ideal for this case but I probably need to make the landing page better.
Re:Ask HN: What are you working on? (June 2026)
on Sunday June 14, 2026 @01:51PM (#48530347)
https://duckville.town
You play a duck in a small shared town. You pick a job, pay rent, post on a Twitter-style feed, vote in local elections. The simulation keeps running when you close the tab. No PvP, no loot boxes, no combat. Playtime is a few minutes a day by design.
Re:Ask HN: What Are You Working On?
on Saturday June 13, 2026 @09:51AM (#48517357)
Thank you :) There is a simple map currently but it can be improved. You can see it on this page after you sign in -> https://duckville.town/city
How can I make it better? I'd be happy to hear your feedback.
Re:Ask HN: What Are You Working On?
on Saturday June 13, 2026 @07:18AM (#48516084)
https://duckville.town
You play a duck in a small shared town. You pick a job, pay rent, post on a Twitter-style feed, vote in local elections. The simulation keeps running when you close the tab. No PvP, no loot boxes, no combat. Playtime is a few minutes a day by design.
Re:Show HN: Duckville, a persistent-world life SIM where you're a duck
on Wednesday April 29, 2026 @04:50PM (#47954430)
Hello, I built it. I'm glad you like it. I'd be happy to hear your feedback
Show HN: Duckville, a persistent-world life SIM where you're a duck
Re:Show HN: Local LLM on a Pi 4 controlling hardware via tool calling
on Tuesday April 14, 2026 @06:35PM (#47772348)
Yes, you can find the instructions here --> https://github.com/stfurkan/pi-llm
Re:Show HN: Local LLM on a Pi 4 controlling hardware via tool calling
on Monday April 13, 2026 @07:03PM (#47759105)
Currently I get around 2 tok/s on the 4B model, and 4-5 tok/s on the 1.7B model.
Re:Show HN: Local LLM on a Pi 4 controlling hardware via tool calling
on Sunday April 12, 2026 @08:05PM (#47745928)
I specifically chose PrismML's 1-bit models because their tiny size allows them to actually fit on smaller hardware like the Pi. The 1.7B model is great for basic tasks and tool triggers, while the 4B model seems reasonable for some daily tasks, though it's much slower on this setup. If you try these models on your M1 Max, I assume they'll run incredibly fast. I previously tried them on a VPS and the inference speed was really good for my experiment.
Re:Show HN: Local LLM on a Pi 4 controlling hardware via tool calling
on Sunday April 12, 2026 @07:14PM (#47745507)
Hi HN,
I spent the weekend experimenting to see if I could get a proper LLM running locally on an old Raspberry Pi 4 (4GB), and more importantly, if I could get it to interact with the physical world.
I ended up using PrismML's new Bonsai models. Because they are genuinely 1-bit (trained from scratch at 1-bit, not quantized down to 4-bit), they actually fit. The 4B parameter model is ~570 MB, and the 1.7B is ~240 MB.
I loaded them through llama.cpp's router mode. I get around 2 tok/s on the 4B model for better reasoning, and 4-5 tok/s on the 1.7B when I just need speed. I tried Gemma 4 E2B first, but it was just too slow on 4GB of RAM.
The fun part: I wired up a cheap TM1637 4-digit display to the GPIO pins. Since Bonsai supports native tool calling, I wrote a small Python proxy that injects an update_display function into requests. When the model decides to use the tool, the proxy catches the streaming call, extracts the text, and drives the display. You can tell it to "show 1453" and it physically lights up.
It’s definitely just a weekend project (7-segment displays can't render W or M, self-signed certs, etc.). The code and setup scripts are all in the repo.
I’m thinking about adding servos or sensors next. Would love to hear your thoughts or see if anyone else is building edge AI hardware projects!
Show HN: Local LLM on a Pi 4 controlling hardware via tool calling
Re:Ask HN: What Are You Working On? (January 2026)
on Monday January 12, 2026 @06:11PM (#46595466)
I've been experimenting with AI Agents to see how far I can push them across different types of complexity (from dashboards to client-side video encoding).
Trip Replay (https://tripreplay.app) - A client-side travel map animator where I successfully got the AI to implement complex D3 projections and WebCodecs logic.
Krypto Markets (https://krypto.markets) – A crypto dashboard built purely in "Agent Mode" to test how fast I could ship a data-heavy UI.
Gez.la (https://gez.la) – My old COVID-era open source virtual tour database project that I used agents to fully refactor and modernize from a legacy stack.
Re:Show HN: Trip Replay – Generate animated travel maps in the browser...
on Wednesday December 31, 2025 @09:38AM (#46444419)
Hello,
I just launched Trip Replay, my last project of 2025.
There are already tools that create animated travel maps, but they are almost all paid apps. Some charge per export, others require a subscription. I wanted something I could use myself without friction. So I built a free, web-based alternative.
How it works: It runs entirely in the browser using Next.js and the Canvas API.
* Rendering: It draws the map (using D3-geo) and the path frame-by-frame on a hidden canvas. * Encoding: Instead of a server-side render, it uses WebCodecs to encode the video directly on the client. * Privacy: Since it's client-side, no data leaves your device (except location search via API).
The output is a 1080p vertical video (9:16) ready for social media.
I launched it on Product Hunt today as well if you'd like to support it there: https://www.producthunt.com/products/trip-replay
The app is live here: https://tripreplay.app
Would love to hear your feedback!