Eve library

@nous/world-model-core

Other

Revision 1

On this page

Shared foundations for the Phase 176 sovereign neural-world-model stack.

Provides the abstractions every learned simulator in Phase 176 builds on:

  • WorldModel<S, A, O> — the uniform interface (encode / step / imagine / getUncertainty) implemented by DreamerV3's RSSM, MuZero's dynamics net, Genie's ST-transformer, and DIAMOND's diffusion dynamics.
  • LatentState — a tagged union of DeterministicLatent, StochasticLatent (diagonal Gaussian), CategoricalLatent (k×c one-hots, DreamerV3), and TokenLatent (VQ codebook grid, Genie), with real KL / entropy / balancing math and flat (de)serialisation.
  • ActionSpace — ContinuousBox, DiscreteFinite, MultiDiscrete, and MultiModal (mouse + keyboard + text), plus a LatentActionCodebook (k-means-fit VQ quantiser) for Genie-style latent action tokens.
  • ReplayBuffer — a prioritised (sum-tree) replay + trajectory dataset that ingests Phase 85 flywheel sessions and serves n-step returns and variable-horizon sequence slices that respect episode boundaries.
  • ImaginationEngine — the DreamerV3 λ-return / GAE rollout engine reused across Dreamer, MuZero, and latent policy-gradient training.

Everything is pure TypeScript with no runtime dependencies; the numeric formulas (KL divergence, λ-returns, prioritised IS weights) are unit-tested against closed-form values.

text
npx vitest run --root libs/nous/world-model-core