Jev: Rule Selection for Claude Code
Jev intelligently selects applicable rules for Claude Code based on prompts and file paths, optimizing context token usage and ensuring relevant rule delivery.
Live radar · scored by Jev
119 signals · last crawl
Jev intelligently selects applicable rules for Claude Code based on prompts and file paths, optimizing context token usage and ensuring relevant rule delivery.
This project built a feed optimizer for X that uses Jev to categorize posts based on probabilities of being ragebait, an ad, low effort, hostile, useful, or savable, which then translates into actions like HIDE, SKIM, or KEEP.
Jev is a tool that intelligently decides which parts of an agent's conversational history are still relevant, reducing context usage and speeding up processing without sacrificing quality.
This project utilizes Jev to enable plain English searches on a job board, allowing users to ask questions directly without needing a predefined schema.
JevQL provides semantic WHERE clauses for vanilla Postgres, powered by Jev.
Built a Chrome extension on @typesafeai s Jev that reads every post in my X feed before I do: one plain sentence re-labels the feed live,scams and ads fade, a large model briefs me on the few posts that matter.
This project is a Chrome extension that allows users to define their own algorithm for viewing content on X, filtering out engagement bait, empty hooks, and ads using plain English rules.
This project scores every event emitted by a machine in real-time, filtering out noise to retain signal, and records these events.
A Chrome extension that filters Twitch live stream chats in real time using TypesafeAI Jev.
This project implements Jev for search and retrieval, where embeddings find candidates and Jev determines which ones the AI client sees.
This project tests the performance of Jev for topic relevance checks within a data processing pipeline.
End of radar