Python · Apache-2.0
OmniJev/OneJev
🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.
★ 230
Stars
21 forks · 0 open issues
+3.1/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
35.1
Momentum / 100
see the breakdown below
41d ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 11.8 | +3.1/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 1.6 | last week ran 1.10× the monthly pace |
| Freshness | 15 | 14.9 | last push 3d ago; decays to zero at 180 days |
| Scale | 15 | 6.9 | 230 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 35.1 | sum of the above |
Detail
| Topics | calibrationcomputer-usedecision-modelgui-agenthuggingfacejevllmmultimodalpytorchqwensystem-onetypesafevideo-understandingvision-language-modelvlm |
| Matched on | LLM & Inference (llm) |
| Short window | +22 stars over 7 days = 3.1/day |
| Long window | +74 stars over 26 days = 2.8/day |
| Lifetime average | 5.91 stars/day over 39 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |