# Zefan-Cai/Open-Jev

> Open-Jev serves a context, questions and candidate answers to Qwen-based models and returns typed probabilities directly, without autoregressive generation or JSON parsing. It provides LoRA adapters, a scalar decision head and a local server for probability decisions over multiple choice candidates.

- Magnitude: 5.2 out of 10 — Early signal
- Stars: 131 total · +8 stars today, ≈ 56 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-09-20 · Last push: 2026-09-21
- GitHub: https://github.com/Zefan-Cai/Open-Jev · Page: https://gitnova.dev/en/r/Zefan-Cai/Open-Jev

## Useful for

- Serve a local Open-Jev checkpoint on GPU and query it over HTTP for probability decisions.
- Compare Open-Jev latency against Jev and OpenAI structured decisions on saved workloads.
- Run the CPU unit tests and JevBench public subset evaluation for the released 2B/9B checkpoints.

## Why it’s here

- 8 stars so far today, about 56 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 2 days old and already has 131 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #143.
- About 14 forks a day — people are taking the code.
- Recent forks include notable developers: @lambda7xx (353 followers).

## 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: 14
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 60 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 9

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-22: 28, 96, 8

## Spotted in now

- Top new repositories this week: #143

## Similar by description

1. **kshetrajna12/reflex** — 2.4 · Early signal · Language models · Python · +2 stars today, ≈ 13 by evening
   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.
   Full card: https://gitnova.dev/en/r/kshetrajna12/reflex.md
2. **Rizzo-AI-Academy/rizzo-flow** — 5.8 · Early signal · Language models · Python · +19 stars today, ≈ 139 by evening
   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 API.
   Full card: https://gitnova.dev/en/r/Rizzo-AI-Academy/rizzo-flow.md
3. **jaredpalmer/kev** — 8.7 · Breakout · Language models · Python · +69 stars today, ≈ 774 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
4. **Yinsongxu/LLM2Jev** — 3.1 · Early signal · Language models · Python · +2 stars today, ≈ 13 by evening
   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.
   Full card: https://gitnova.dev/en/r/Yinsongxu/LLM2Jev.md
5. **ekzhang/openjev-sglang** — 2.3 · Cooling · Language models · Python · +1 star today, ≈ 10 by evening
   HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.
   Full card: https://gitnova.dev/en/r/ekzhang/openjev-sglang.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 2026-09-22 08:04 UTC, updated every 30 minutes.