GX10-1 — Artemis
NVIDIA GB10 Grace Blackwell · Qwen orchestration
Strategic brain. Task decomposition, research, queue control, stuck-work detection.
Six machines. One continuous loop. The lab runs 24 hours a day — writing code, reviewing it, deploying it, and trading with it. Here's how it fits together.
Click a node to highlight its role in the mesh. Work moves across a shared filesystem — no message broker required. If the internet drops, the lab keeps running.
Interactive mesh — select a node to pin focus. Deselect by clicking again.
Each machine has a dedicated role. Work is passed between them over a shared NAS filesystem — no message broker, no cloud dependency. If the internet goes down, the lab keeps running.
The strategic brain. Reads everything happening in the lab, decides what to fix next, and writes task definitions that the rest of the pipeline executes. Runs the Artemis agent loop and hosts the primary Qwen3.5-122B model for orchestration and research.
The implementer and quality gate. Takes task definitions from Artemis and generates precise code patches. Also hosts the local patch reviewer — Qwen3.5-122B running on port 8081 (ctx 65K, reasoning 512) — which scores every patch before it can advance to staging.
The hands and the hub. Hosts the shared NAS filesystem that all agents read and write. Also runs the Deployer and Tester agents: receives staged patches, validates them, and applies changes to production files via SSH. Dual RTX 3090 NVLink for local inference.
The trader. Runs TradeShadow — an autonomous momentum strategy on 14 Kraken pairs. Completely isolated from the pipeline: it only receives research findings, never pipeline patches. Capital is real.
The command centre. Runs OpenClaw — the AI assistant gateway routing tasks between Claude, Grok, and xAI. Hosts PI (the primary assistant), peer review timers, and the live lab dashboard backend. The machine you reach when you message PI.
Dedicated local inference node. Runs Ollama with a library of open-weight models including Qwen3-Coder. Provides fast GPU-accelerated inference for coding tasks, model evaluation, and background analysis without competing for VRAM on the pipeline nodes.
Artemis → Forge → Tester → Deployer. A cycle starts when a research finding or user request lands in the incoming queue. From there, everything is automatic — from task definition through to production deployment.
Two additional systems run on independent timers — TradeShadow and the Qulix nightly cycle. Neither touches the core pipeline; they feed findings back into it.
A momentum trading system running on 14 Kraken spot pairs. Completely isolated from pipeline code changes — it only receives research findings as input, never patches. Every trade is logged to analytics and reviewed weekly to guide future research priorities.
Each night, the lab generates a fresh edition of Qulix — a public-facing blog that translates what the pipeline has been doing into plain English. It pulls live pipeline stats, TradeShadow outcomes, and research findings, then writes and publishes without human intervention.
All inter-machine communication happens through the shared NAS filesystem. No message queues, no databases, no cloud APIs for internal routing. Plain files, atomic writes, directory polling.