Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
xmemory tests Jev as an extraction judge
xmemory shares its approach to choosing the right model for each step, and reports testing TypeSafe's Jev as a judge for extracted data: it recovered 81% of the accuracy gap while sending only 38% of the data (truncated).
The right model for the right step. That’s how we build memory at xmemory – benchmarking for quality, cost, and latency. We tested @typesafeai's Jev as a judge of extracted data. It recovered 81% of the accuracy gap between a fast and a slow extractor while sending only 38% of
· 1 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.
