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.
TypeSafe AI are the providers for Jev. This complaint is like saying it’s a red flag that Claude Code sends lots of information to somewhere called Anthropic.
Ah, well that makes a bit more sense. Admittedly I haven’t really looked into Jev and thought it was an open decision model rather than a proprietary product from TypeSafe.
Confirmed: Jev is TypeSafe’s product, and that’s the decide/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/phones/addresses are not. Full table: https://github.com/Avinash-jetwani/jevmem/blob/main/SECURITY...