Yumii is an open-source, locally-run AI companion featuring a Live2D avatar, real-time voice, and six personalities, now capable of long-term memory across sessions. It prioritizes accessibility with easy installation, comprehensive documentation, and a streamlined onboarding process, developed for the GitHub Finish-Up-A-Thon Challenge.
Long-running AI agents require persistent memory for learning, context reduction, and decision auditing, but current systems treat memory as mere storage, leading to issues like unregulated growth and forgetting. This paper proposes Governed Evolving Memory (GEM) as a new data-management workload, where correctness is a property of the state trajectory.
This text discusses how effective memory systems are crucial for AI agents to evolve into genuine collaborators, enabling them to recall interactions and learn from feedback. It highlights the distinction between short-term and long-term memory as key to designing seamless, personalized, and robust AI systems.
Modern AI systems struggle with memory, often forgetting past interactions or relying heavily on Retrieval-Augmented Generation (RAG). MemPalace introduces a novel approach to build structured, persistent memory for AI agents, overcoming the limitations of constant reliance on external data.
O texto aborda o desafio de criar agentes de IA com memória de longo prazo, destacando que a limitação arquitetônica atual impede a construção de agentes relacionais úteis em escala. Ele critica o custo e a latência de simular memória com janelas de contexto grandes, defendendo arquiteturas mais inteligentes que armazenam e recuperam memória externamente.
A maioria dos agentes de IA sofre de amnésia devido aos limites da janela de contexto e custos, perdendo raciocínios acumulados. O desafio está na qualidade da recuperação e no custo por token, sendo a solução mais inteligente a recuperação seletiva, ranqueada e comprimida, com projetos como Remembr liderando essa abordagem.
This article explores how modern AI agents utilize short-term (STM) and long-term (LTM) memory, drawing parallels to the human brain's memory system. It defines STM in AI as temporary memory for ongoing interactions and LTM as persistent storage beyond single sessions.