Aureis is a desktop-native operator console for autonomous trading, market intelligence, execution routing, and continuous strategy evolution. The public download is a signed x64 Windows installer for the desktop app; its trading engine runs inside a Docker container that Aureis loads and SHA-256-verifies on first launch, so every operator runs the same tested runtime instead of a fragile per-machine dependency stack. Docker Desktop must be installed and running.
Aureis is in Beta. Expect regular updates as bugs are fixed, packaging is tightened, and release channels mature. Inside Neural Chat, users can run `/linting` to help surface and clean up bugs and issues in the code base.
The ancient aureus was not just currency. It was a trust layer stamped in gold: standardized under Caesar, refined under Augustus, and carried through the empire as a compact proof of value, sovereignty, and settlement. Aureis borrows that lineage, then inverts it for a harder future: after central banks buckle under cascading debt crises, capital controls, and synthetic liquidity games, free markets have to be rebuilt from verifiable rails instead of decrees.
What Aureis is
Aureis is designed as more than a trading app. It is a desktop command center that combines autonomous strategy agents, market intelligence, reinforcement-learning driven iteration, and multi-venue execution into one operator surface. The goal is not prettier charting. The goal is to reduce the gap between what the market is doing and what your infrastructure can understand, decide, and execute.
Operator cockpit
Aureis puts autonomous execution behind a single desktop control plane: live oversight, release-aware installs, market context, wallet and venue visibility, and a command surface built for operators instead of dashboard tourists.
Agentic market execution
The platform coordinates AI agents and strategy bots across centralized venues and on-chain rails, routing action from research to decision to execution while preserving explicit operator control.
Continuous strategy evolution
Reinforcement-learning and backtest loops are built into the stack so strategies are not frozen in one market regime. Aureis is designed to adapt as liquidity, volatility, and venue behavior shift.
Auditability under pressure
Trade logs, update metadata, and export-oriented flows reduce the usual operational blind spots around releases, PnL history, and tax preparation when markets move faster than people can reconcile by hand.
Origin story
The historical aureus became valuable because it compressed trust into something portable, scarce, and legible. It was used for major payments, military salaries, and stored wealth precisely because settlement confidence mattered more than ornament. But the aureus also carries the warning: weight and purity decayed as the empire stressed its own foundations.
Aureis turns that history into product fiction with a practical core. In a future where central banks fracture credibility, capital controls harden, and closed financial systems fail to clear honestly, markets re-open first where settlement is visible. Blockchain rails provide the ledger. Agentic AI provides the execution layer. Aureis sits between them, coordinating bots, research, and operator decisions so value can move through open networks instead of collapsing institutions.
Problems Aureis is designed to solve
Aureis is built for the operational failures that precede financial failure: fragmented liquidity, delayed human reactions, brittle bots, poor observability, and trust bottlenecks around settlement. The platform exists to make those seams visible and tradable again.
When liquidity is fragmented across exchanges, smart contracts, and internalized flows, human operators lose the market map. Aureis is designed to restore visibility and route intelligence.
Manual workflows break when markets reprice in seconds. Aureis compresses observation, reasoning, and execution into a tighter loop without removing the operator from the chain of command.
Static bots decay. Aureis is built to test, retrain, and revise strategies against real market conditions so automation does not ossify into a liability.
If settlement guarantees degrade, value migrates toward verifiable rails. Aureis is aimed at open, programmable markets where blockchain settlement and agentic coordination can outlast institutional failure.
The Aureis timeline
Julius Caesar fixes the aureus near eight grams of high-purity gold and turns a coin into a state-backed promise of settlement.
The coin finances empire, military pay, and stored wealth. Over time, weight and confidence erode under pressure, proving that even dominant monetary systems can dilute themselves into fragility.
In the Aureis story, central banks overextend, currencies fracture, and the world reaches for hard settlement again. Gold returns as signal, but software becomes the mint.
Aureis AI agents create open market structure on blockchain rails: transparent execution, programmable intelligence, and a market standard that can be verified instead of merely announced.
Release channels
The public-recommended path is the complete x64 offline installer. Aureis publishes direct artifacts, update metadata, SHA-256 checksums, and a machine-readable release manifest so installs are inspectable instead of opaque.
Signed Windows package that installs the Aureis desktop app. It pairs with Docker Desktop: the containerized trading engine is SHA-256-verified and loaded on first launch, then cached for instant subsequent starts — so the runtime is identical on every machine.
SHA-256: f655778283db24dad313522a755c30ccac9111dc558a150c4d13fa8bfe247983
Required runtime · install this first
The Aureis desktop app is a thin control surface. The heavy lifting — the trading engine, the Neural Brain Matrix memory, the bot fleet, and the local LLM stack — runs inside a Docker container that Aureis loads and supervises for you. Docker Desktop must be installed and running before you start Aureis. If Docker Desktop is not running when you launch the app, the engine cannot boot and Aureis will wait at startup until it can reach the container.
Why a container
Aureis depends on a precise Python 3.12 runtime, native trading and ML libraries, and a market-data stack that is notoriously brittle to install per-machine. Shipping the engine as a prebuilt container image means every operator runs the exact same, tested environment — no missing DLLs, no compiler mismatches, no "works on my PC" drift.
Why a container
The engine is pinned byte-for-byte in the image and verified by SHA-256 before it loads. Your trades, keys, and memory live in mounted host folders, while the runtime stays sealed inside the container — so an upgrade can never half-patch your machine and a bad release rolls back cleanly.
Why a container
Because the runtime lives in the container rather than scattered across your system, Aureis does not pollute your global Python, PATH, or system services. Removing Aureis is as simple as deleting the app and its image — your Windows install is left untouched.
Why a container
The default image is CPU/cloud-first so it boots fast on any PC. If you have an NVIDIA GPU, the same container model lets Aureis opt into local GPU inference and reinforcement-learning training (Docker Desktop + WSL2 GPU + the NVIDIA Container Toolkit) without changing how the rest of the app runs.
First-run order
Before you begin
Aureis is a Windows-first desktop app whose trading engine runs inside a Docker container — a pinned Python 3.12 runtime, a CCXT-based market layer, and an optional llama.cpp/Ollama local LLM stack. Docker Desktop is required. Plan capacity around Docker and the engine container, not the UI.
Operating system
64-bit Windows 11 only. Server 2022 is supported for headless paper-trading deployments. Aureis is not built or tested against Windows 10, Apple Silicon, or Linux.
Container runtime · required
Aureis runs its engine in a Docker container, so Docker Desktop must be installed and running before you launch the app. On Windows it uses the WSL2 backend (enabled during Docker setup). See the Docker section above for the download and first-run order.
Hardware baseline
For the local LLM and full bot fleet, 32 GB RAM and an 8-core CPU are recommended. NVIDIA RTX 30-series or newer (CUDA 12+) accelerates local inference; CPU-only mode works but is slower for chat.
Disk space
The desktop app is small, but the Docker engine image (~3.3 GB) plus Docker Desktop's WSL2 virtual disk consume real space, and WSL2 grows on demand. Reserve additional headroom for model files, OHLCV cache, and trade history.
Network
First launch downloads the engine image once (~680 MB compressed) unless it shipped bundled with the installer. Live trading then requires reachability to your configured exchange (e.g., Bitunix, Binance via CCXT). The local LLM runs offline; cloud LLM fallback only fires if explicitly configured with provider keys.
Install steps
Standard install
Aureis-Setup-1.1.5.exe).certutil -hashfile Aureis-Setup-1.1.5.exe SHA256. Match the digest to the value shown above or in SHA256SUMS.txt.%LOCALAPPDATA%\Aureis). This lays down the Aureis desktop app; the trading engine is loaded as a Docker container on first launch.%APPDATA%\Aureis for the Neural Brain Matrix, bot configs, and trade history.Post-install verification
A successful install does not yet mean a successful trading deployment. Walk this checklist before enabling live trading on real capital.
With Docker Desktop running, open Neural Chat. The status pill should read "Backend ready" within ~60 seconds once the engine container is healthy. If it stays on "Booting", confirm Docker Desktop is running, then check %APPDATA%\Aureis\backend.log.
Type a short message in chat. The first response confirms the local LLM (Ollama / llama.cpp) inside the engine container is running. Cloud fallback is optional and disabled by default.
Open the Bots panel. You should see the default fleet (volatility_scalper, breakout_tracker, smc_reversal, market_making, grid_integrator, tdi_mfi_reversal) all in paper_trading mode.
Configure exchange API keys under Settings → Exchanges. The connectivity probe must pass before flipping any bot to live mode. Live trading without a successful probe is blocked.
Troubleshooting
Most common: Windows blocked the launch
Symptoms: double-clicking the desktop or Start Menu shortcut produces no window, but launching C:\Program Files\Aureis\Aureis.exe from a terminal works. This means SmartScreen, Windows Defender, or a third-party antivirus has put a "Mark-of-the-Web" hold on the installed files or is silently sandboxing them.
One-click recovery: download the launch helper below, right-click Help-Aureis-Launch.cmd and choose Run as administrator. The helper unblocks every file in C:\Program Files\Aureis\, optionally adds a Defender exclusion for that folder, and then launches Aureis.
Both files must be saved into the same folder (e.g. your Downloads). Double-click the .cmd only — the .ps1 is invoked automatically.
SmartScreen warning during install
Click More info then Run anyway. The Aureis installer is Authenticode-signed, but SmartScreen reputation accrues with download volume — until then the warning is expected. Verify SHA-256 against SHA256SUMS.txt first if in doubt: certutil -hashfile Aureis-Setup-1.1.5.exe SHA256.
Two folders appeared on your Desktop
If you see $PLUGINSDIR and an Aureis folder on your Desktop, the installer was extracted (e.g. via 7-Zip or "Extract All") instead of being run. NSIS installers are technically archives, so Windows will happily unpack them. Delete those two folders, re-download Aureis-Setup-1.1.5.exe, and double-click it (or right-click → Run as administrator) — do not extract.
Antivirus quarantined Aureis
Add C:\Program Files\Aureis as an excluded path in your antivirus product. Most third-party AV vendors expose this under "Settings → Exclusions / Allowed Items / Trusted Locations". On Windows Defender, the launch helper above does this for you (with admin elevation). After excluding, re-launch via the desktop shortcut.
Engine won't start
Aureis runs its engine in a Docker container, so Docker Desktop must be running before you launch the app. Open Docker Desktop and wait until the tray whale icon reports "running", then relaunch Aureis. If Docker Desktop isn't installed yet, get it from the Docker section above. On a true first launch the engine image downloads once (a few minutes on a slow link) before the app is ready.
Backend never readies
The Electron UI is up but the FastAPI backend at http://127.0.0.1:8000 is not responding. Read the tail of %LOCALAPPDATA%\Aureis\backend.log for the actual python exception. Common causes: port 8000 occupied by another process, antivirus locking python.exe, or a corrupted SQLite schema (the latter is auto-repaired starting in 1.1.0).
Local LLM very slow
Aureis defaults to local-first execution with a 5s timeout before cloud fallback (if configured). On CPU-only systems, expect slower local generation; consider enabling cloud fallback for chat-heavy workflows.
Failed update
Re-download the installer over a clean network and re-verify SHA-256 with certutil. A persistent mismatch indicates a corrupted download or a CDN propagation lag — wait a few minutes and retry.
Download Aureis 1.1.5 · 2026-05-29
The recommended public download is the complete x64 offline installer. Verify the SHA-256 locally before installing. The artifact set is generated from the local build output and published to Cloudflare R2 with byte-range and resume support for large downloads.
SHA-256 // Aureis-Setup-1.1.5.exef655778283db24dad313522a755c30ccac9111dc558a150c4d13fa8bfe247983
certutil -hashfile Aureis-Setup-1.1.5.exe SHA256. The expected SHA-256 is published above and in SHA256SUMS.txt./linting in Neural Chat to help surface and clean up bugs and code issues while the platform is in Beta.https://aureisai.com.Single-file Windows build with the full runtime bundled inside. No first-launch runtime download required.
Cryptographic checksums for every published binary in this release. Verify locally before installing.
Compact JSON metadata for in-app update prompts and release checks.
Published update metadata for release channels.
Machine-readable artifact inventory for this public release.
Human-readable release upload checklist and artifact map.