Eve library

@nous/genie

Other

Revision 1

On this page

Orchestration for Genie-class action-conditioned world models (Phase 176.5). The trained dynamics plug in through the WorldDynamics interface; a deterministic ReferenceWorldDynamics (a real navigable closed-form world) makes the whole stack runnable and testable without a GPU.

  • WorldSession — the durable, resumable session: deterministic seed, prompt log, pose-keyed @nous/wm-memory MemoryBank, input/frame history, mid-session re-prompting, a transport boundary (WebRTC video + input, fail-loud when absent), and a serialisable durable state tree.
  • GenieWorldService — the /maya/genie/create endpoint: text prompt → interactive world session, persisted to a SessionStore (in-memory default; MinIO in 176.8.1.2), with resume-after-eviction. (176.5.1.5)
  • AdversarialPromptController — the "adversarially prompt your experience" PvP mode: multiple players submit world-rewrite prompts, arbitrated by priority
    • per-player cooldown, broadcast through a @maya/multiplayer binding. (176.5.2.2)
  • EducationScene — the @metis/lessons wrapper: a teacher prompt plus learning objectives + assessment hooks, tracking real exploration state (regions visited, prompts issued, pose) and emitting progress reports. (176.5.2.3)
  • Trainable video stack (nous_genie/) — exact-default 8×16×16 VQ-VAE tokenizer with a 16,384-entry EMA codebook, causal eight-code latent action model, and action/prompt/persistent-memory-conditioned autoregressive dynamics. The full 11B recipe is represented without allocating it in local gates.

Not included (external — left unchecked in TODOS)#

The large-dataset training, published-quality interactive rollouts, and ≥24 FPS 720p B200 result in 176.5.1.1–176.5.1.4 require large-scale accelerated training on hundreds of thousands of video hours. Their locally actionable architectures and conditioning paths are implemented above.

text
npx vitest run --root libs/nous/genie
cd libs/nous/genie && python3 -m pytest tests-python/ -q