◈Bluesky50
YHacker News50
XX / Twitter50
listening to
Jev
150
mentions
tracked
tracked
net sentiment
+25%
48 positive
92 neutral
10 negative
volume & sentiment over time
Sep 25, 2026 · Daily
sources
most discussed
decision / models
active days
1
what people keep raising
- decision / models 36
- built 15
- models 9
- model 7
- open-source / alternative 4
- performance 3
mentions
Showing 76–92 of 92 mentions
-
Y Hacker News 1w neutral builtJevmem – automatic project memory for Claude Code, built on JevCurious how this compares to my own tool, https://deciduous.dev I will have to give it a run-through today. I haven't used Jev yet so this should be interesting. I'd be interested to see if any Deciduous users have opinions, too. Curious how this compares to my own tool, https://deciduous.dev I will have to give it a run-through today. I haven't used Jev yet so this should be interesting. I'd be interested to see if any Deciduous users have opinions, too.view source ↗
-
Y Hacker News 1w neutral decision / modelsJevmem – automatic project memory for Claude Code, built on Jevjevmem 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 Reversed decisions get marked superseded. Install: npm i -g jevmem… 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 Reversed decisions get marked superseded. Install: npm i -g jevmem (needs a TypeSafe API key) 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. 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.view source ↗
-
Y Hacker News 1w ▲ 58 neutral builtJevmem – automatic project memory for Claude Code, built on Jevview source ↗
-
Y Hacker News 1w ▲ 1 neutralSmall questions, measurable gains with Jev – CraftCXview source ↗
-
Y Hacker News 1w ▲ 2 neutralJev and Reasonersview source ↗
-
Y Hacker News 1w neutralShow HN: Jev Plays Pokémon RedJev can't come up with original text, but I did consider giving it a list of hilarious names. Jev can't come up with original text, but I did consider giving it a list of hilarious names.view source ↗
-
Y Hacker News 1w ▲ 5 neutral builtJev Is Built for Tinkerersview source ↗
-
Y Hacker News 1w ▲ 2 neutralReAnchor, a Jev Optimizer in DSPyview source ↗
-
Y Hacker News 1w ▲ 2 neutral modelA Jevlike using an escalation model to route between a classifier and an LLMview source ↗
-
Y Hacker News 1w ▲ 3 neutral modelsBenchmarking Jev, Laya, and five open models under three stressesview source ↗
-
Y Hacker News 1w ▲ 1 neutralMy Take on Jevview source ↗
-
Y Hacker News 1w ▲ 2 neutralShow HN: JevPertus – Jev-style option scoring on Apertusview source ↗
-
Y Hacker News 1w ▲ 1 neutralJev CEO talk: I made ChatGPT, now I'm building what's next [video]view source ↗
-
Y Hacker News 1w ▲ 2 neutralI made a linter using Jev for things a regular linter can't catchview source ↗
-
Y Hacker News 1w ▲ 3 neutralShow HN: Herobrine – Minecraft buddies using jevview source ↗
-
Y Hacker News 1w neutral modelShow HN: Jevper – the Jev interface on top of any OpenAI-compatible modelas an alternative option to Jev, and to take advantage of LLM's reasoning for the classification. as an alternative option to Jev, and to take advantage of LLM's reasoning for the classification.view source ↗
-
Y Hacker News 1w neutralJev Based Code ReviewBut isnt the whole point of Jev that "we trained it so you dont have to"? Yet it make such a simple mistakes still. But isnt the whole point of Jev that "we trained it so you dont have to"? Yet it make such a simple mistakes still.view source ↗