Xytro Labs
Where you own your data.
What it does
Valis AI is a privacy-first AI assistant and OpenAI-compatible API. • Ghost mode — conversations leave no trace • API with adaptive semantic caching (repeat calls ~7.5% cost) • Sign in with Google or a Xytro Account — identity hashed, never sold • Part of Xytro Labs: email, cloud, identity. No tracking. No ads. No data selling.
Xytro Labs makes AI and cloud tools that respect your privacy: Valis AI (AI assistant), Xytro Post (email), The Vault (cloud storage), and Xytro One (unified identity). Where you own your data.
Xytro Labs builds AI and cloud services that keep your data yours. Our flagship app, Valis AI , is a private, sign-in-based AI assistant for chat, writing, and automation — plus private email, cloud storage, and a unified account. No tracking, no ads, no data selling. Sign in with Google to get started. Xytro Labs lets you use modern AI and cloud services without giving up your data. It is a single account, one sign-on, and a private home for your digital life — across email, storage, and AI chat. An intelligent AI assistant for chat, writing, and automation. Chat privately with an adaptive semantic cache, ghost mode that stores nothing, and your own API keys at ai.xytro.site.…from xytro.site
Does the same job
all alternatives →
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 · 16d 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, 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 · 16d ago · simedw.com