Settings

Theme

Show HN: File-base agent memory framework, like Claude's skills

github.com

2 points by k_kiki 23 days ago · 0 comments · 1 min read

Reader

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 makes memory opaque and hard to inspect, especially for temporal or multi-step reasoning.

An alternative is to make memory readable and structured: store it as files, preserve raw inputs, and allow the LLM to read memory directly instead of relying only on vector search.

No comments yet.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection