mohit67890/imajev
Open Jev-style typed-decision model that also takes images: photo + app state + typed questions in, calibrated probabilities out, locally.
About the project
Open 2B/4B/9B models that take photos, records and text and return probabilities over the options you set, with an explicit can't-tell. Runs locally so your system acts when sure and hands the rest to a person.
Useful for
- Check a product photo against listing fields and name the contradicted field
- Compare a reference photo with a returned one and get a match probability
- Route a ticket by category and score urgency without sending data off-site
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 35 stars so far today, about 46 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 6 days old and already has 110 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #139.
- About 6 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 110
- Today
- 35 · ≈ 46 by evening
- Forks
- 10
- Issues and pull requests
- 3
- Watchers
- 0
- Language
- Python
- License
- Apache-2.0
- Created
- September 23, 2026
- Last push
- September 29, 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 29, 2026Top new repositories this week: #139
Similar by description
-
0.7
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.
-
1.1
Davipar/djev-dev
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.
-
0.6
allebee/jevk5
An open-weight alternative to TypeSafe Jev: given a state (ticket, log, policy, diff) and a yes/no, choice, or score question, it returns a probability for every option in one forward pass with zero generated tokens.…
-
2.7
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.
-
4.3
Liuziyu77/Valen
A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo…
-
2.0
Mapika/decider
A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model…