Aartiq
For Questions That Matter
What it does
AI that can do things shouldn't do them silently. Aartiq is an open-source AI browser that plans tasks, explains consequential actions, requests permission, then executes — through a six-layer defense-in-depth security model with 525 automated tests. Every action is gated. Every sensitive command requires your approval. Your files, your device, your data — they stay yours. Plan → Explain → Ask → Execute One student. One question. One centimeter between capability and authority.
Aartiq is a local-first, open-source AI-native browser with a built-in assistant, local LLM support (Ollama), permission-gated OS automation, and end-to-end encrypted cross-device sync. Built by Preet Patel (Ponsri School) with Electron, Next.js, and TypeScript.
“The most important question isn't what you ask AI. It's what AI asks you before it acts.” Aartiq™ is an open-source AI browser that plans tasks, explains non-trivial actions, requests permission when required, and executes through controlled capabilities. The distance between what AI can do and what it is allowed to do. That one centimeter is the space Aartiq leaves for you to decide. Everything below shows it in practice. Say: “Clean up my Downloads folder.” Aartiq reaches for context — then stops at the boundary and asks. The only phase that can slow the whole system is Ask . That is intentional. Many AI systems are optimized to complete the task when context is incomplete. Aartiq treats…from aartiq.ponsrischool.in
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