Davipar/djev-dev

Structured decisions with DiffusionGemma and vLLM. Native image inputs, image choices, live camera sampling, and a compact one-step inference path.

Language modelsPython

3.6 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 22, 2026, 08:48 UTC.

Open on Seismograph Open on GitHub

About the project

An open implementation of small typed decisions (yes/no, choice, score) on DiffusionGemma and vLLM, with native image and camera input. It reads allowed-label probabilities instead of generating prose or JSON.

Useful for

Route support tickets by deciding urgency and team from the text
Match an image against a reference and pick the closest option among pictures
Rate quality on a rubric and get a probability distribution over levels

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

6 stars so far today, about 27 expected by the end of the day.
The spike has held for 3 days in a row — not a one-off blip.
The repository is 3 days old and already has 98 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Top new repositories this week: #189.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 98
Today: 6 · ≈ 27 by evening
Forks: 5
Issues and pull requests: 1
Watchers: 2
Language: Python
License: Apache-2.0
Created: September 19, 2026
Last push: September 19, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 22, 2026Top new repositories this week: #189

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/Davipar/djev-dev.svg?lang=en)](https://gitnova.dev/en/r/Davipar/djev-dev)

Similar by description

2.4
kshetrajna12/reflex
An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.

Early signalLanguage modelsPython+3 stars today, ≈ 13 by evening
5.5
receptron/laya
TypeScript wrapper for running the open-source Laya System-1 decision model via ONNX Runtime: takes a state and typed questions, returns answers with calibrated probabilities in one forward pass.

Early signalLanguage modelsTypeScript+14 stars today, ≈ 87 by evening
5.9
Rizzo-AI-Academy/rizzo-flow
A local-first implementation of the Jev idea: an LLM returns typed decisions (boolean, choice, score, numeric) with probabilities in a single forward pass, without generating tokens. Compatible with the TypeSafe HTTP…

Early signalLanguage modelsPython+29 stars today, ≈ 145 by evening
3.6
razorback16/openjev
An open-source "System One" decision server on DiffusionGemma: send a state and typed questions (yes/no, choice, score) and get probabilities plus confidence in tens of milliseconds, with no text generated.…

Early signalLanguage modelsPython+2 stars today, ≈ 25 by evening
4.9
deepopen-com/deepopen
Open-source non-autoregressive System 1 decision engine for typed decisions: returns typed answers (choice, score, noul) in a single forward pass across 100+ languages without generating text. Suited for…

Early signalLanguage modelsPython+29 stars today, ≈ 102 by evening
8.9
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.

BreakoutLanguage modelsPython+197 stars today, ≈ 1,251 by evening