persistent-knowledge

WikiSkill introduces a framework that co-evolves agent skills with a persistent knowledge base to systematically accumulate experience and improve performance across models, demonstrating benefits over state-of-the-art skill-evolution methods.

ShadowFrog is an open-source system that builds a persistent shadow knowledge base for coding agents, enabling them to remember code across sessions and improve bug detection, retrieval, and feature ideation through autonomous exploration.

An independent developer quietly shipped a working “LLM Wiki” system—persistent memory for language models—weeks before Andrej Karpathy publicized the same concept.