LIVE STUDY / 001

What you imagine.

What we can build.

AI assistants · Learning systems · Intelligent software
MEET NYX

Meet Nyx.

Local AI models. An interface that makes sense.

01 / VISUAL GUIDANCE

A clearer next step.

Explanations and highlights. You stay in control.

02 / APPLE-NATIVE

At home on your Mac.

macOS first. iPhone and iPad support planned.

03 / SCREEN-AWARE

Starts with your screen.

Designed to understand visible context through OCR.

04 / LOCAL-FIRST

Intelligence, on device.

On-device AI. iCloud sync for chats and files is planned.

SCROLL TO EXPLORE
NYX / IN DEVELOPMENT
BY ARJIA

Introducing

ARES ENGINEBY ARJIA

MACHINE LEARNING · MARKET RESEARCH

Ares

Question
the signal.

An open-source engine that turns public market data into tested models and paper signals.

Move or touch to explore

Public Coinbase and Kraken candles. Checked together before they become a research dataset.

OPEN SOURCE / MITRESEARCH & PAPER INFERENCESCROLL TO EXPLORE

INSIDE THE ENGINE

Trust is a condition.
Not a default.

Ares checks the input before it trusts the output. Change the feed below. See what gets through.

DATA INTEGRITY LAB
INTERACTIVE SIMULATION
03 / ACCEPTED28 / 28 CANDLES VERIFIED
PUBLIC INPUTETH / USD
Coinbase Kraken
ENGINE DECISION
Ready for research

Fresh, complete data passes every check.

PASS / VALIDATED INPUT
FreshnessPASS
Venue agreementPASS
ContinuityPASS

Illustrative scenarios, including simulated recovery. No live exchange connection or orders.

EVIDENCE OVER INSTINCT

The future stays
out of training.

Learn from the past. Leave a gap. Test on what the model hasn’t seen.

Ares uses chronological evaluation with fees, slippage, and doubled-cost stress. Models earn their place through evidence.

Read the research protocol
WALK-FORWARD VALIDATION01 / 04
Train Gap Test
PASTTIME →UNSEEN

Window 01. Train on the earliest data, then evaluate on the next unseen period.

Select a window to follow the expanding training history.

BUILT TO BE EXAMINED

Open the hood.

Explore the research. Inspect the decisions. Make it better.

Explore Ares Engine on GitHub
ARJIA / ARES ENGINEResearch software. Paper signals only. No live orders or promise of returns.Back to the beginning ↑
ABOUT / ARJIA TECHNOLOGIES

Meet your
specialist.

Gabriel Williams / Founder & software engineer

I turn ideas into software with purpose, character, and clear limits.

Arjia is my independent practice in applied AI and product engineering. I build websites, custom software, and user interfaces, connect the systems behind them, and automate workflows with AI.

3D SCANGW — 001
THINK

Architecture first.

Understand the problem, constraints, and consequence.

MAKE

Ideas made tangible.

Build the interface and the system behind it.

PROVE

Work you can examine.

Publish the evidence, decisions, and limits.