k_kiki

↗ HN profile [ 35.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. We’ve been experimenting with what a real *“always-on” proactive agent* could look like, and built one called *memUbot*. It runs 24/7 in the background, keeps track of what you do, and builds long-term memory from it.…

  2. You can think of it as a memory toolbox. Memory is stored not only as vectors, but also as readable natural language, so everything you save remains visible. When needed, the system retrieves relevant memories and makes…

  3. AI memory systems often become a black box. When an LLM produces a wrong answer, it’s unclear whether the issue comes from storage, retrieval, or the memory itself. Most systems rely on RAG and vector storage, which…

  4. Hi HN, We’ve been building memU(https://github.com/NevaMind-AI/memU), an open-source, general-purpose memory framework for AI agents. It supports dual-mode retrieval: classic RAG and LLM-based direct file reading. Most…