linear-recurrence

interactive, sub-16ms vector explainer built for the DataForge 2026 Pathway Track.It proves why classical State Space Models suffer exponential associative forgetting ($\rho(A)^L$) and visualizes how Pathway's Dragon Hatchling (BDH) synaptic plasticity and BDH CQ continuous latent reasoning eliminate interference without KV-cache explosion.

Chunked parallel associative scan in Triton: varlen packing, bidirectional, torch.compile. Drop-in primitive for gated linear RNNs.

Python implementation for automatically solving linear homogeneous recurrence relations with constant coefficients using the characteristic polynomial method

Three-path memory for LLM agents: KV window (exact attention) + retrieval index (archived chunks) + TRN recurrent state (8-96 KB, O(1) per step)