# TheoLeeCJ/SemIf-OpenJev

> An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.

- Magnitude: 6.4 out of 10 — Peaking
- Stars: 4,032 total · +107 stars today, ≈ 208 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-09-16 · Last push: 2026-09-21
- GitHub: https://github.com/TheoLeeCJ/SemIf-OpenJev · Homepage: openjev.com · Page: https://gitnova.dev/en/r/TheoLeeCJ/SemIf-OpenJev

## Useful for

- Route support tickets to queues by reading model logits directly
- Benchmark direct logit readout against autoregressive JSON generation on a 3090
- Reuse one long state across 21 criteria via shared mode

## Why it’s here

- 107 stars so far today, about 208 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 7 days old and already has 4,032 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this month: #18.
- Hacker News: “OpenJev” — 720 points, 5 days ago.
- About 39 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 266
- Issues and pull requests: 36
- Watchers: 12
- Average over the last week: 580 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 9

## Stars per day, last 11 days (oldest → newest, today is partial)

2026-09-13 … 2026-09-23: 0, 0, 0, 75, 964, 613, 384, 581, 791, 519, 107

## Magnitude by day, last 7 days

09-17 7.3, 09-18 8.7, 09-19 8.1, 09-20 6.9, 09-21 7.3, 09-22 7.4, 09-23 6.6

## Hacker News

- OpenJev — 720 points, 296 comments: https://news.ycombinator.com/item?id=49752041

## Spotted in now

- Top new repositories this month: #18

## Similar by description

1. **hr98w/jev-visual** — 2.4 · Cooling · Language models · Python · +6 stars today, ≈ 10 by evening
   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.
   Full card: https://gitnova.dev/en/r/hr98w/jev-visual.md
2. **jaredpalmer/kev** — 9.0 · Breakout · Language models · Python · +682 stars today, ≈ 1,172 by evening
   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.
   Full card: https://gitnova.dev/en/r/jaredpalmer/kev.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-23 15:36 UTC, updated every 30 minutes.