Native Tavern
Fully compatible with SillyTavern,smoother mobile experience
What it does
NTavern is native cross-platform mobile application (iOS and Android) that reimplements SillyTavern as a high-performance native app with full compatibility for SillyTavern data formats. This is a tool app，If you want to use it, please bring your own official apikey for large models such as deepseek,qwen, anthropopic, gemini, etc. before you can use it. Al chat tool that can import SillyTavern character cards - simple and easy to use.
Does a similar job
all alternatives →- OFObsidian for Mobile – Plain-text knowledge base on the go2021 · obsidian.md · ▲760
- IBI built a virtual tabletop for playing Dungeons and Dragons2023 · diceright.com · ▲395
Diceright is a virtual tabletop for playing dungeons and dragons with friends on the web. You can watch a quick overview of how it works here: https://tinyurl.com/diceright. And there’s a list of the main features right on the homepage. It’s a Ruby on Rails site that makes heavy use of action cable for keeping the maps and tokens in sync for all players. On the front end, I’m using HTML canvas for the maps and a js library called fabric.js for interacting with the canvas. Otherwise, just jQuery on the front end. I optimized it all to work on mobile too. I built this as a side…
- SBSkip – Build native iOS and Android apps from a single Swift codebase2024 · skip.tools · ▲322
Hello Hacker News. I'm Marc, one half of the team that created skip.tools. Skip is a tool that transpiles your SwiftUI iOS app into a Kotlin Jetpack Compose app, and enables you to use a single language to create a complete app that reaches the entire mobile marketplace. What it is: Skip stands in contrast to other cross-platform development tools like Flutter, React Native, and Xamarin, in that it enables the creation of genuinely native applications for both of the dominant mobile platforms. It doesn't embed a separate engine or runtime into your app, but instead lets you use pure Swift…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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 · 28d ago · cactuscompute.com
