The half of the workshop
where the robots work.

A roster of governed agents with eval gates, audit trails, and memory with provenance. They triage, summarize, investigate, and file their own receipts.

A Strix Halo rig running a 190+ model fleet behind a routing gateway. Chat, embeddings, vision, voice, and image generation without leaving the building.

Flipper Zero, ESP32s, breadboards, a 3D print pipeline with its own MCP server, and wearable capture experiments. Solder smoke included.

Self-chaining job schedulers, daily blog generation, deploy gates, and the boring glue that keeps a hundred repos honest.

DB-isolated security analysts, read-only eval contracts, and a healthy distrust of anything that can't show its logs.

Every day the pipeline drafts what got shipped, a human approves it, and it lands here. The receipts of the whole operation.

Agents propose; the operator approves. Nothing gets promoted to durable truth or production without a human decision on the record.

Every agent runs against a declared grant profile. If live grants drift from the manifest, certification blocks until they reconcile.

Read-only contracts proven by deterministic test fixtures before an agent activates. The security analyst passed its isolation suite before it touched anything.

Every LLM-backed decision is traced. Agents produce claims; git and the warehouse hold the evidence. If it is not observable, it did not happen.