# OmniJev/OneJev

> A multimodal System One decision model that returns calibrated probabilities for typed questions about screenshots, photos, video and text in a single forward pass. Available in 0.8B, 4B, 9B and 27B.

- Magnitude: 4.1 out of 10 — Early signal
- Stars: 83 total · +0 stars today, ≈ 43 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-09-27 · Last push: 2026-09-30
- GitHub: https://github.com/OmniJev/OneJev · Homepage: https://omnijev.github.io/OneJev/ · Page: https://gitnova.dev/en/r/OmniJev/OneJev

## Useful for

- Estimate the probability that a GUI agent has completed a task from a screenshot
- Pick the agent's next action (click, type, scroll, stop) with a probability distribution
- Fine-tune the model on your own data via train.sft with cross-entropy and Brier loss

## Why it’s here

- 0 stars so far today, about 43 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 4 days old and already has 83 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #172.

## 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: 10
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 25 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 6

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-01: 4, 14, 5, 60, 0

## Spotted in now

- Top new repositories this week: #172

## Similar by description

1. **InternLM/Intern-Decision** — 4.1 · Early signal · Language models · Python · +0 stars today, ≈ 50 by evening
   A multimodal decision model built on Qwen3.5 that turns a state, optional images, and typed questions (choice, score, yes/no) into decisions with probabilities. Ships with training, two inference backends, temperature calibration, and a…
   Full card: https://gitnova.dev/en/r/InternLM/Intern-Decision.md
2. **malevrigns/agent-jev** — 1.1 · Cooling · AI agents · Python · +0 stars today, ≈ 4 by evening
   AgentJev-0.6B is a specialist decision model for AI agent loops: it takes unstructured state (diffs, traces, logs) plus typed questions and returns a probability distribution over options in a single forward pass with zero token decoding.
   Full card: https://gitnova.dev/en/r/malevrigns/agent-jev.md
3. **receptron/laya** — 2.3 · Steady · Language models · TypeScript · +0 stars today, ≈ 29 by evening
   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.
   Full card: https://gitnova.dev/en/r/receptron/laya.md
4. **jaredpalmer/kev** — 2.8 · Cooling · Language models · Python · +0 stars today, ≈ 85 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
5. **NandhaKishorM/laya** — 3.4 · Cooling · AI agents · Python · +0 stars today, ≈ 382 by evening
   Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.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 2026-10-01 03:34 UTC, updated every 30 minutes.