MinimalChat – A Simple and Customizable LLM Chat Application
Hello everyone! I have a hobby project that has become fairly full featured that I figured I would share. The idea of MinimalChat has been to create a project that is a lightweight and dead simple application that can be deployed locally in a few seconds (with docker). While of course also having most of the nice to have features and looking pretty nice. A nice bonus is it a Progressive Web Application so it can be installed like a normal application to your mobile device. It has a full mobile UI. For those using Chrome and Edge you can also locally download, load and host entirely via your…
What it does
In the maker’s words, at launch
Hello everyone! I have a hobby project that has become fairly full featured that I figured I would share. The idea of MinimalChat has been to create a project that is a lightweight and dead simple application that can be deployed locally in a few seconds (with docker). While of course also having most of the nice to have features and looking pretty nice. A nice bonus is it a Progressive Web Application so it can be installed like a normal application to your mobile device. It has a full mobile UI. For those using Chrome and Edge you can also locally download, load and host entirely via your browser models like LLama-3-8b with hardware acceleration via WebGPU. It's pretty experimental but it does work! I won't bloat this post reiterating it's features, the GitHub Readme gives a good idea of the application abilities. I know chat applications are a dime a dozen but...here's another one hah!
Does the same job
all alternatives →- AWA weekendproject, disposable web chats2012 · beta.mss.gs · ▲74
Create a chat, copy the URL, paste it wherever you want. Perfect for those that would like to continue a discussion on a social network without having to sign up for anything. http://beta.mss.gs/#!/page/home
- HIHipmob is Olark for mobile apps. (Live support chat, now on Android)2012 · hipmob.com · ▲51
- FIfaces.io – ridiculously simple video chat2014 · ▲40
This is something fun I’ve been hacking on recently: ridiculously simple group chat. Go to http://faces.io and then get your friends to do the same. That’s it! :-D Currently works best in Chrome. It’s definitely beta status at best. Audio can get weird—be ready to mute. ;-) Let me know what you think!
- CSChat Simply – Group chat for everyone2014 · ▲6
Today my friends and I are launching a project we've been hacking on for the past few years. It's friendly web based group chat (with apps for Mac, Windows, and iOS) that's not limited to a single business. It basically offers the power of XMPP with a simple UI. chatsimply.com Please check it out and let me know what you think!
- MCMamba-Chat – A Chat LLM Based on State Space Models2023 · github.com · ▲9
Hey everyone! Many of you might have come across the Mamba paper a few days ago, which introduced an LLM based on a state space model architecture. The Mamba architecture is quite useful as its complexity scales subquadratically with input length and is therefore way more efficient than transformer models: https://github.com/state-spaces/mamba I got really excited about the paper, so I decided to fine-tune the model on a chat dataset. It turns that this actually worked quite well! The model is quite suitable for casual chatting, which honestly surprised me given that it…
- MWmy weekend project, Vidless. "CloudApp" for video chat.2012 · vidless.com · ▲16
I always find myself frustrated by how many steps I have to take to video chat with someone online. There's always too much software to download and install, and too many accounts to remember. The high-end, high-price Cisco conferencing systems I've used are especially fragile. So I built Vidless in a weekend for myself, and I hope you find it useful too. Just create a room and share the link, and you'll be chatting in seconds. You can invite several people (I haven't really tested a max yet), and chats on Vidless are always private. Enjoy!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
