daseinlabs/open-jev
Open Jev implementation with custom finetuning
About the project
Local server and CLI for scoring pre-written options with an LLM: computes each option's log-probability in a single prefix-shared forward pass without decoding, running Gemma 3 4B on Apple Silicon via MLX.
Useful for
- Rank assistant reply options by probability to pick the best one
- Start the HTTP server on :8000 and score options in about 90 ms per request
- Answer typed questions (choice, score, noul) via the TypeSafe System One contract
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 1 star so far today, about 9 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 5 days old and already has 95 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #197.
- Hacker News: “Open-jev: One-pass option scoring with Gemma 3 4B, similar to jev” — 6 points, 5 days ago.
- Recent forks include notable developers: @pjt3591oo (384 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 95
- Today
- 1 · ≈ 9 by evening
- Forks
- 17
- Issues and pull requests
- 9
- Watchers
- 1
- Language
- Python
- Created
- September 17, 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.
Hacker News discussions
- Open-jev: One-pass option scoring with Gemma 3 4B, similar to jev6 points, September 17, 2026
Spotted in
- September 22, 2026Top new repositories this week: #190
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/daseinlabs/open-jev)Similar by description
-
3.1
Yinsongxu/LLM2Jev
A tool that turns local language models into structured decision engines: it accepts Choice, Score, and Noul questions and returns typed answers with probabilities using prefill-only inference without generating tokens.
-
3.4
hr98w/jev-visual
An educational project for running vision-language model inference on Apple Silicon via MLX: answers multiple questions about one image by choosing options or scoring levels, without autoregressive generation.
-
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…
-
4.8
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…
-
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.
-
8.8
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.