Lumbridge Compute

Governed compute for unified-memory AI hardware — the machines where CPU and
GPU share one pool and there is no separate VRAM allocation to bounce off.
Over-commit that pool and the box thrashes and wedges, SSH and ping included,
before the OOM killer gets a turn.

Compute does not run inference. It supervises the servers that do:

- Admission control. A model starts only if committed + requested + margin
  fits the budget. The refusal is the feature.
- A 1 Hz watchdog on MemAvailable that stops the newest model before thrash.
- Scenes: named sets of models activated as one transactional unit, with
  pre-flight validation and rollback to the previously active Scene on
  failure. Scenes reference model ids, never weight paths or commands, so a
  Scene obtained from elsewhere cannot introduce code.
- Process ownership bound to (boot_id, pid, start_time_ticks, pgid == pid),
  so a reused PID can never be group-killed.
- A protocol-transparent TCP gateway, so clients keep one address while model
  runtimes move behind it.
- An MCP server, so agents drive the node as tools rather than as a CLI.

One binary, six direct dependencies, no async runtime outside the MCP surface.

Published from the internal monorepo with a fresh history. The private
development tree keeps its own history; nothing here carries it.

examples/demo/scenes/one.scene.yaml

@@ -0,0 +1,12 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: one
+  version: 1
+  description: "Demo scene one: alpha + beta."
+models:
+  - alpha
+  - beta
+activation:
+  order: footprint-asc
+  wait_healthy: true