Jevmem – automatic project memory for Claude Code, built on Jev
by avinashjetwani on 9/25/2026, 4:04:04 PM
https://github.com/Avinash-jetwani/jevmem
Comments
by: anthuswilliams
One interesting quirk of the AI-written READMEs these days is how they can include every detail on how it works, thoroughly document every optional flag, known limitation, experimental result, and still not communicate the essence of the project and the problem it solves.<p>I have read through the project and I still don't understand what this thing is for and why it is to be preferred over the harness's native memory management tools.
9/25/2026, 4:25:53 PM
by: rafram
> When you change your mind, the old line is marked superseded, not deleted<p>To me, this seems like a design error. You're polluting context with false/outdated information (even if the LLM is instructed to ignore it). The biggest issue with the memory systems built into Claude et al. is that they're terrible at pruning old/conflicting information as the project evolves, so I'd hope a replacement would do something to improve that.
9/25/2026, 4:45:17 PM
by: joshumax
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.
9/25/2026, 4:48:36 PM
by: alpineman
a supercollision of 2024 hype with 2026 hype
9/25/2026, 4:30:31 PM
by: rhgraysonii
Curious how this compares to my own tool, <a href="https://deciduous.dev" rel="nofollow">https://deciduous.dev</a><p>I will have to give it a run-through today.<p>I haven't used Jev yet so this should be interesting. I'd be interested to see if any Deciduous users have opinions, too.
9/25/2026, 4:33:16 PM
by: shaohua
something I always wanted
9/25/2026, 4:22:49 PM
by: saagarjha
Wake me up from this nightmare
9/25/2026, 4:33:07 PM
by: avinashjetwani
jevmem watches Claude Code, Cursor & Codex chats and keeps a JEVMEM.md in your repo up to date. After each message, Jev (TypeSafe) decides whether anything is worth remembering — a decision, a bug, a change of mind — and writes the keepers to that file. Reversed decisions get marked superseded.<p>Install: npm i -g jevmem (needs a TypeSafe API key)<p>Held-out check on 66 messages (23 Sep 2026) vs six frontier LLMs: save/skip 98.5% (tied with Astra); save+correct kind 95.5% (Astra 98.5%, Opus 97.0%); changes of mind 5/5; median 0.30s via Jev API (~0.6s end-to-end) vs 2.8–4.3s for the LLMs; cost $0.000127/decision. Single run by me — treat 1–2 message swings as noise.<p>Limits: early v0.4; fully automatic only in Claude Code today (Cursor/Codex via agent/MCP); messages go to the TypeSafe API with secrets stripped; if the API is down it skips.
9/25/2026, 4:05:14 PM