Upfyn and UpfynAI
A council of great minds working on your local machine.
What it does
Upfyn is an AI that works on your actual machine — opens your files, fills in forms, drives your browser and runs on a schedule. Say what you need; it does it, with your approval. Windows app, free to start.
Speak to one local-first assistant in two modes: Analyst coordinates analysis and everyday work; Developer coordinates development. Your permissions set the boundary.
Hand over the folder. Get back only the ones that do not match. Talk to the same assistant in both modes. Analyst coordinates research, documents and scheduled work. Developer coordinates the full project, terminal, browser, Git and specialist tools. Both run through the local desktop engine. Analyst and Developer are the front door. Install only the focused workspaces you need; they share the same projects, permissions and local engine. Draft cited documents, edit them in place, and keep the result beside the work it came from. Your apps already hold the work. Speak the outcome, and Upfyn coordinates the context and approved actions across them — turning your machine into your own AI…from upfyn.com
Does the same job
all alternatives →
Perplexity Personal Computer for WindowsJun 2026 · perplexity.ai · ▲127Run AI agents across your local files and apps on Windows
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 · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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