O

Business AI

OpenJev

Run Jev-style typed decisions locally: in-browser or on a 3090

stars syncing from GitHub MIT

OpenJev reproduces the Jev interface pattern with open models: read typed option probabilities directly from a model's logits - no answer sentence, JSON repair, or decoding loop. On a single RTX 3090 with frozen Qwen3.5-4B, 21 decisions complete in 1.0 seconds with zero output tokens (5.2x faster than autoregressive JSON, identical results), and shared-state reuse pushes throughput to 20 decisions/second on 777-decision workloads. On the 102-row TypeSafe subset, the open 4B model reaches 0.845 balanced accuracy against Jev's published 0.883. Ships as a browser-only WebGPU demo (no waitlist, no backend) and a Python scorer with pinned model revisions, prompt hashes, and raw results with checksums. The repo states plainly it does not reproduce Jev's undisclosed model or training.

At a glance

Primary use case

Same judgments as Jev, on your own hardware: batch classification of records, content moderation screens, agent step decisions (retry / route / pause), form routing, dataset tagging. The browser demo needs no install and no API key - 21 questions in one second on a 3090. Best fit when you want typed decisions without sending code or data to a third party.

Who's behind it

TheoLeeCJ (independent)

GitHub stars
https://github.com/TheoLeeCJ/openjev
syncing from GitHub
License
MIT
Platforms
browser, cli
Install
pip install -e '.[test]'
Model support
Open models: Qwen3 0.6B, MiniCPM5 2B, Qwen3.5 4B (GGUF browser / BF16 CUDA)