Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Laya Local Benchmark: 630ms Decisions on Pure CPU
Benchmarked Laya on an old laptop (i5-5200U, 12GB RAM, HDD). It achieved sub-second (~630ms) decisions on CPU alone, no GPU or cloud LLM needed. An open-weight release suitable for fast routing.
Benchmarked Laya locally on an ancient laptop: 💻 i5-5200U (2 cores) | 12GB RAM | 5400 RPM HDD Kept it resident in RAM and got sub-second (~630ms) typed decisions on pure CPU! 🔥 Great open-weight release by @Nandakishorm1. No GPU or cloud LLM needed for fast routing. #laya #jev
· 2 likesOpen on X
More like this
Training an MLP on Qwen 4B to Replicate Jev Behavior
The author shares an open-source project openjev that trains an MLP on qwen 4b to work like Jev, with a Hugging Face link. Link
Swapping an agent's tool-calling reasoning with Jev
The author shares replacing an agent's tool-calling reasoning with Jev, using Fable, Astra, and Opus; early results show drastic savings with very close results, with a demo video promised.
