Von.dev – Lovable and Cursor and Roo in One Tool
Hey HN – We made [Von.dev](https://von.dev), an AI-native development environment to build full-stack apps. Our differentiations: Multiple Tech Stacks (Python and React), AI model selection, VS Code in browser, Use your own Openrouter key, Deep Data Integration such as google sheets and many more We are currently in beta. Looking for feedback from devs building serious tools or internal apps who want more power than current AI coding assistants offer. Try it here: [https://von.dev](https://von.dev) Happy to answer any questions! - Harsh
In plain words
Von.dev is an AI-native development environment for building full-stack applications. It supports multiple tech stacks including Python and React, allows users to select their preferred AI model, includes VS Code in the browser, and integrates with data sources like Google Sheets. Users can provide their own Openrouter API key. The tool is designed for developers building serious applications or internal tools who need more capability than standard AI coding assistants. Currently in beta.
written from the facts on this page · September 2026
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
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
