veldt-kya

DNA-inspired memory layer for AI agents: zero-LLM-call ingestion, retrieval that beats full-context on overflowing histories.

Cut your LLM prompt size by 40-70% in one line of code -- semantic chunking + extractive summarization that preserves meaning, instructions, and key entities.

CHAP adapter for AG2 (AutoGen): record a human-decision envelope at the human-input turn.

LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.