Lumbridge Compute

Governed compute for unified-memory AI hardware — 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 against two ceilings — a declared budget, and what the
  machine actually has free. The refusal is the feature.
- A 1 Hz watchdog on MemAvailable that stops the newest model before thrash,
  and defers to a Scene transition rather than racing it.
- 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.
- A read-only HTTP API for dashboards: loopback by default, CORS off unless an
  origin is named, and it never mutates.

One binary, six direct dependencies, no async runtime outside the MCP and API
surfaces. Apache-2.0.

Generated from the internal monorepo by scripts/publish-compute.sh, which
refuses to publish a tree it cannot prove clean.

examples/demo/registry/models.yaml

@@ -0,0 +1,34 @@
+apiVersion: lumbridge/v1
+version: 1
+
+# GPU-free demo registry: each "model" is just a tiny HTTP server so you can watch
+# Lumbridge Compute activates scenes, swap models, and run the watchdog on any Linux box.
+# Run from the repo root:  lumbridge-compute --root examples/demo scene activate two
+
+models:
+  alpha:
+    name: "Demo Alpha (http.server)"
+    footprint_gb: 1
+    health: "http://127.0.0.1:9101/"
+    serve:
+      kind: exec
+      port: 9101
+      command: ["python3", "-m", "http.server", "9101", "--bind", "127.0.0.1"]
+
+  beta:
+    name: "Demo Beta (http.server)"
+    footprint_gb: 1
+    health: "http://127.0.0.1:9102/"
+    serve:
+      kind: exec
+      port: 9102
+      command: ["python3", "-m", "http.server", "9102", "--bind", "127.0.0.1"]
+
+  gamma:
+    name: "Demo Gamma (http.server)"
+    footprint_gb: 1
+    health: "http://127.0.0.1:9103/"
+    serve:
+      kind: exec
+      port: 9103
+      command: ["python3", "-m", "http.server", "9103", "--bind", "127.0.0.1"]

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

examples/demo/scenes/two.scene.yaml

@@ -0,0 +1,12 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: two
+  version: 1
+  description: "Demo scene two: beta + gamma (keeps beta, swaps alpha->gamma)."
+models:
+  - beta
+  - gamma
+activation:
+  order: footprint-asc
+  wait_healthy: true