Live data from Hacker News

Viewing profile — AttentionBlock

AttentionBlock

HN member
Joined
Tue, May 11, 2021, 9:59 PM UTC
HN karma
30
Public activity
10 items

About AttentionBlock

diaa1999abujaber@gmail.com

Recent public activity

  1. comment
    Comment #46637613

    great question claude-mem uses a compaction approach. It records session activity, compresses it, and injects summaries into future sessions. Great for replaying what happened. A-M…

  2. comment
    Comment #46637025

    Thanks for the feedback I am planning to extend for other agents. But now it should work with some caveats. I have configured claude specific hooks, the hooks keeps reminding Claud…

  3. story
    Show HN: A-MEM – Memory for Claude Code that links and evolves on its own

    Hi HN, I have been recently geeking on agentic memories, and I believe I finally came up with something that works. I spent the last couple of weeks building a memory[0] for Claude…

  4. comment
    Comment #46580217

    meta-analysis, make Claude write a blog post, connecting and deriving set of concepts across a range of books, articles, papers, etc. Basically a syntopic reading machine. Its a me…

  5. comment
    Comment #46572633

    Thanks for the pointer! But it seems to me beads is a different tool? Beads is a task tracker for multi-agent system, A-MEM is agentic memory for accumulated knowledge.

  6. story
    Show HN: Persistent Memory for Claude Code (MCP)

    This is my attempt in building a memory that evolves and persist for claude code. My approach is inspired from Zettelkasten method, memories are atomic, connected and dynamic. Exis…

  7. comment
    Comment #46415535

    > It’s a cynical way to view the C-staff of a company. I think it’s also inaccurate: from my limited experience, the people who run large tech companies really do want to deliver g…

  8. story
    Show HN: I built an app where AI models debate real Polymarket events

    Inspired from my experience with LLM as a judge

  9. comment
    Comment #44091938

    Using LLM as a judge architecture to optimize multi-agent system prompts and configurations. For now it's achieved through LLM based consensus system that evaluates another LLM out…

  10. comment
    Comment #35321323

    Paywall-ed and extra not available in my country :(