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.
Interactive
Free
Launch Team / Built With
Brave Private Browser
Arc
Dia Browser
Hey, Product Hunt. 👋
Some boundaries shouldn't be crossed without asking first.
That became Aartiq.
"The most important question isn't what you ask AI. It's what AI asks you before it acts."
Most AI agents are optimized to complete tasks when context is incomplete. Aartiq treats missing context differently — when authority is unclear, it stops and asks. That behavior is enforced by a capability policy you can read in the source. Not configured. Enforced.
Before any non-trivial action, Aartiq:
→ Plans the task
→ Explains what it intends to do
→ Asks for your permission
→ Executes — only after you say yes
Six independent security layers back this up. 525 automated tests verify it on every push. Every claim on our security page links to the source file or test that proves it. Inspect, don't trust.
What happened to my private diary should never happen to a computer system.
That one sentence is why this exists.
Started on an Intel i5, 8 GB RAM, while preparing for JEE exams. Now at v0.3.6 — Windows, macOS, Linux, Android. Apache 2.0. Fully open source.
Development is paused while I finish exams. The repository is live, the security model is intact, and every release will still be there when I return.
Aartiq is 1 CM away from the future.
The "1 CM" is a personal reminder that respecting a boundary begins with asking before you cross it.
What would you want an AI browser to ask you before it acts? Tell me below. 👇
— LatestInssan