The primitive layer of LLM-native knowledge systems — a memory substrate where documents are the smallest unit of intelligence infrastructure.
-
Updated
Jun 9, 2026 - Python
#
memory-substrate
Here are 3 public repositories matching this topic...
Memory as advisory for LLM agents — forgets noise, keeps what matters. Lazy exponential decay, four-op API, OpenUSD cold tier. Python ≥3.11. Patent-pending.
python memory ecs usd cognitive-architecture handle vector-search llm openusd llm-agents memory-ai agent-memory memory-substrate memory-decay memory-ai-agent codeless-schema
-
Updated
May 5, 2026 - Python
Evidence-Bound Retrieval (EBR) — accretive memory for AI agents. Amendment records, structural precedence, BM25. A substrate for CoALA's episodic memory layer.
ehr coala bm25 episodic-memory ebr clinical-ai language-agents agentic-memory memory-substrate evidence-based-retrieval
-
Updated
Jun 9, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the memory-substrate topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the memory-substrate topic, visit your repo's landing page and select "manage topics."