X · by MajoSayo

LogJev

Text, images or audio in, choices and scores out of the logprobs.

さよ☆マギカ

@MajoSayo

I wanted Jev-style decisions with my own models, so I built LogJev. Text, images or audio in; choices/scores from logprobs. Node + Python, agent skills, cloud or local (requires modality + logprobs support). 2048 demo: github.com/DumoeDss/logjev

Sep 22, 2026 · 0 likesOpen on X

LogJev is a Node and Python project that takes text, images or audio and produces choices and scores from the logprobs. It runs in the cloud or locally, and ships a 2048 demo.

Open the source

Hide posts on X in plain language

tamara

@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

XTools and apps

Pick

Instant compaction for Claude

Zachi

@iam_zachi

I think I just cooked something 🔥 jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function. WHERE jev(people, 'could work from home') or WHERE jev(people, 'name sounds european') 129 rows judged in ~1s for $0.0009. Second run: 6ms from cache.

XTools and apps

jev() for PostgreSQL

Rows judged: 129 in ~1 s

LogJev

More like this

Hide posts on X in plain language

Instant compaction for Claude

jev() for PostgreSQL