Lab & internal · 2026
Jetson edge inference nodeLive
An NVIDIA Jetson Orin Nano running local language models as the lab's free, private default brain for classification and first-pass triage.
Cloud models are fast and sharp; they also cost money and see your data. The Jetson is the answer for everything that does not need a frontier model: news bucketing, first-pass classification, and anything that should never leave the network.
Notes from running small models for real
- A 3B model on the default 4K context silently returned empty results when the prompt overflowed. Raising the context window and shrinking the batch fixed it; the lesson was to measure output, not trust it.
- Thermal and fan telemetry from the board is read over SSH and shown on the status board, because a throttled node looks exactly like a slow model.
At a glance
StatusLive
TypeLab & internal
Year2026
AI
OllamaQwen 2.5Local inference
Stack
NVIDIA Jetson Orin NanoUbuntuOllamaPrivate mesh
Related work
Athena — AI command center
Lab & internal
ClaudeOpenAIOllama CloudLocal Ollama (Jetson)+6
A private, always-on console that triages email across inboxes, monitors AI and breach news, tracks weather, and runs the company back office — with four interchangeable LLM providers behind one router.
Touchscreen status panel
Lab & internal
Consumes AI-triaged feedsActs on model outputRaspberry Pi10-inch touch display+4
A wall-mounted, always-on touch display on a Raspberry Pi that shows what matters at a glance — inbox items needing a reply, today's schedule, live weather radar, storm and breach alerts — and lets you act on them with a tap.
Google Workspace MCP server
Lab & internal
MCPClaudeClaude CoworkTypeScript+6
A self-hosted Model Context Protocol server that gives Claude scoped, multi-account access to Gmail and Calendar — with encrypted tokens, dry-run-by-default bulk actions, and a click-to-add account flow.