Open-source SRT translator and quality-control tool that sends each source–translation pair to Jev as a Noul decision, then flags suspected omissions or meaning changes for human review without automatically rewriting subtitles.
This is an independent community listing. Check the source, license, data handling, and evaluation caveats before relying on a project. Inclusion is not an endorsement or security review.
Home Assistant integration that turns typed questions about entity state into sensors and automation actions, with entities reporting daily calls, tokens, and estimated cost and a token budget that halts evaluation; answers carry no explanation, so it is not suitable for safety decisions.
Android overlay that reads visible QQ and X conversations through accessibility, Feishu/Lark text through on-device OCR, and WhatsApp one-to-one chats (validated only against recordings), asks Jev for typed intent, danger, and next-action judgments, has a separate text model draft three replies that Jev ranks, and fills a selected reply without sending it; other device tests are author-reported, and chat content goes to the configured model APIs.
Web search demo using Jev's typed Choice and Noul judgments to select sources, time ranges, and query candidates, then rank results retrieved through Search1API; relevance scores are model judgments, not verified accuracy.
Download share card
