Python · Apache-2.0
nokia-applied-research/AnyJev
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
★ 1.6k
Stars
179 forks · 12 open issues
+7.9/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
41.2
Momentum / 100
see the breakdown below
48d ago
Created
last push 17d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 18.1 | +7.9/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.48× the monthly pace |
| Freshness | 15 | 13.8 | last push 17d ago; decays to zero at 180 days |
| Scale | 15 | 9.3 | 1.6k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 41.2 | sum of the above |
Detail
| Topics | calibrationdecision-modeljevjev-modelllmsystem-onetransformersvllm |
| Matched on | LLM & Inference (llm) |
| Short window | +55 stars over 7 days = 7.9/day |
| Long window | +430 stars over 26 days = 16.5/day |
| Lifetime average | 35.00 stars/day over 45 days |
| First seen here | 2026-10-11 |
| Last read | 3d ago |