Technology
Aura is not a collection of apps. It is a stack: presence, intelligence, memory, perception, a model, a runtime, and verification around all of it. Scroll, and follow one request down through the layers and back up to you.
Out loud or typed. KIRA hears you and shows that Atlas is listening. Intelligence should not feel like another dashboard.
An answer, a live search, a visual, an edit. It plans the work before any model runs.
What you saved, and why it mattered. Your own context, brought back with your permission.
If there is an image or footage, it sees it. It can tell a letterbox bar from a genuinely dark scene.
Today Atlas runs open-weight Qwen 3.5 models. Nucleus is our research into smaller, sharper ones. Bigger is not the only path to better.
It reads your machine and picks the model size, memory, threads and GPU layers that fit right now. The decision takes under a millisecond.
Each claim is checked against its sources and marked supported, partial or unsupported. You see the verdicts, not just a confident tone.
Barx 2.0 · Shipping in Atlas Runtime
Every time Atlas answers, Barx reads the machine: memory, pressure, cores, GPU, disk, power. Then it picks the model, context, threads and GPU layers that fit. Try it. This is the actual Barx policy, running in your browser.
The same policy has Python and PowerShell ports for Windows and Linux, parity-tested at 42 of 42 identical plans. The machine presets here are examples.
GlassBox Lite · in Atlas Verification
Every Atlas answer passes through GlassBox. It pulls out the claims, then checks each cited claim against the exact source text the model read. You get a verdict and the evidence, not just a confident tone. It runs in milliseconds with no model call.
Matching is lexical today, so a faithful paraphrase can read as partial. We would rather show you that than hide it.
The Moon orbits at an average distance of about 384,400 km from Earth [1]. It is slowly drifting away, by about 3.8 cm each year [2]. The drift is caused by tides transferring Earth's rotational energy to the Moon [2]. In a few million years it will be too far to cause solar eclipses.
In development and research
We label everything by what it is today. A product is something you can use. Research is a direction we are investigating.
In development
An on-device memory layer. Thoughts, voice, screenshots, photos and links, kept with why they mattered and brought back when they help. Processed on your device where possible, synced through your own platform account where needed.
Research
Visual intelligence. Our first problem: fill a 16:9 screen with a 2.39:1 film without cropping a genuinely dark scene. It samples small patches about every 0.7 seconds and stops the moment real image appears in the bars.
Research
Our foundation model research: efficient reasoning in small models that run on CPUs and Apple silicon without a server. We will publish results when they are benchmarked and reproducible.
Models & credits
Atlas runs open-weight models locally through Barx. We name them, because trust starts with telling you what is inside.
Qwen is a trademark of its owner. Aura is not affiliated with or endorsed by the Qwen team.