‹ BackHN Continuity

Thread

Jevmem – automatic project memory for Claude Code, built on Jev

62 points · 49 comments · avinashjetwani

  1. rhgraysonii · · focus · HN ↗
    Curious how this compares to my own tool, <a href="https:&#x2F;&#x2F;deciduous.dev" rel="nofollow">https:&#x2F;&#x2F;deciduous.dev

    I will have to give it a run-through today.

    I haven&#x27;t used Jev yet so this should be interesting. I&#x27;d be interested to see if any Deciduous users have opinions, too.

    1. 0x457 · · focus · HN ↗
      deciduous seems like a great way to ensure there is no space left in context for useful work.

      Problem with all these automatic memory managment tools is that they can&#x27;t reliably classify if something is useful or not. Once it start using some tool it will heavily become biased towards using that tool during that session. First you will have decision to use postgres as a database, by the end of session it will start saving &quot;decided to use SELECT query for this method because that is how you pull data out of database&quot;.

      1. avinashjetwani · · focus · HN ↗
        That’s the hard problem, and I don’t pretend it’s solved. jevmem’s bet is a save&#x2F;skip gate (Jev probabilities + fixed thresholds in config), not &quot;log every turn.&quot; On a held-out set of 66 messages I wrote, save&#x2F;skip was 98.5%; that is a single author-built run, and I have not measured long-run drift or whether injected lines actually improve answers. Trivial &quot;used SELECT&quot; lines should fail the content&#x2F;importance gates; if they don’t in real use, that’s a bug I want labeled with `jevmem wrong` &#x2F; `missed` so `fit` can retune. Happy to hear where deciduous draws that line too.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.