HN Explorer

mvyshnyvetska

↗ HN profile [ 33.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Breathe-Memory – Associative memory injection for LLMs (not RAG) (github.com)

    LLMs forget. The standard fix is RAG — retrieve chunks, stuff them in. It works until it doesn't: irrelevant chunks waste tokens, summaries lose structure, and nothing actually models how memory works. Breathe-memory…

    6 points 1
  2. Show HN: Semantic-diff – understanding intent, risk and impact behind Git diffs (github.com)

    Hi HN — I built semantic-diff for myself, and it turned out surprisingly useful. Regular git diff shows what changed. semantic-diff tries to answer: – why was this change made? – what could break? – what should the…

    2 points 2
  3. A three-layer memory architecture for long-running agents

    Anthropic's recent piece on effective harnesses for long-running agents hit close to home. We've been wrestling with the same problems — agents that try to one-shot everything, declare victory prematurely, and leave…

    1 points 0