‹ BackHN Continuity

Thread

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

62 points · 49 comments · avinashjetwani

  1. joshumax · · focus · HN ↗
    I’m looking at the LLM-generated SECURITY.md and this thing seems to pump a LOT of information back to some place called TypeSafe AI. That and the AI-generated comments from OP here make a few red flags go up for me.
    1. avinashjetwani · · focus · HN ↗
      Confirmed: Jev is TypeSafe’s product, and that’s the decide&#x2F;recall step. Each turn we send the scrubbed user message (and sometimes the assistant reply), the previous two turns, and live memory lines to score — no telemetry. Credential-shaped secrets, emails, and card-shaped numbers are redacted first; names&#x2F;phones&#x2F;addresses are not. Full table: <a href="https:&#x2F;&#x2F;github.com&#x2F;Avinash-jetwani&#x2F;jevmem&#x2F;blob&#x2F;main&#x2F;SECURITY.md" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Avinash-jetwani&#x2F;jevmem&#x2F;blob&#x2F;main&#x2F;SECURITY...
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.