Memory system for LLMs that remembers everything you teach it during conversation. No reindexing, no context window limits. CPU by default, GPU optional.
-
Updated
May 1, 2026 - Python
Memory system for LLMs that remembers everything you teach it during conversation. No reindexing, no context window limits. CPU by default, GPU optional.
A non-Transformer hierarchical recurrent network with differentiable Gumbel-Softmax routing and bounded memory slots. Runs 7B+ parameter models layer-by-layer on low-budget GPUs.
A viewer whose perception evolves with each image—stateful, memory-carrying VLM reflections across a gallery.
Deterministic control, memory augmented agent runtime
Independent implementation of memory-augmented prompt optimization
🌟 Build efficient models with Transformer Hierarchical Layers for powerful text processing and enhanced performance in natural language tasks.
Add a description, image, and links to the memory-augmented topic page so that developers can more easily learn about it.
To associate your repository with the memory-augmented topic, visit your repo's landing page and select "manage topics."