NNETSKY LAB  // AI/ML R&D
N 51°30′26″
W 0°7′39″
SCALE 1:1
2026.04
FIG. I
TOP-DOWN VIEW
HOVER A NODE
Solo AI/ML R&D · public workbench

Netsky
Lab— engineer the seams.

Netsky Lab — a lab of one. Independent R&D on the substrate models actually run on: bounded context, run continuity, model surgery, inspectable agent memory. Public on GitHub — code first, claims after.

Operatorsolo Focussubstrate engineering Proofopen work
Click any node to open the dossier
§ 01method

How the lab actually runs.

I.

Models need instrumentation.

Training runs, fine-tunes, and local inference fail silently unless runs, configs, failures, and evaluation traces are first-class engineering objects. Most teams treat them as logs and wonder why nothing reproduces.

II.

Agents need memory.

A capable agent should remember what failed, what was verified, what policy changed, and what the next run must read before editing code. Without that, every session is a stranger to the last.

III.

Context is bounded.

Token budgets are not hoarded. Context gets ranked, admitted, broadcast, and evicted through capacity-limited workspaces that can be inspected — gating and broadcast are engineering objects, not folklore.

IV.

Research needs receipts.

Claims should point to sources, quotes, traces, benchmarks, byte-stable manifests, or code. A beautiful answer without provenance is still a liability.

V.

Open work beats mystique.

The public org is meant to be inspected. If the work is good, the code should carry more weight than the landing page.

§ 02reach

Where to reach the lab.

The work lives at the seams — where model behavior, memory, and evaluation refuse to compose cleanly.

Specific substrate over stacks. The public repos are the work, not the pitch.

Concrete over conceptual.

Questions and proposals — channels below.