Five repos for testing Jev on support email routing instead of Claude
Drawing on the Jev article's point, the author lists five open-source repos to test letting a cheap decision layer route emails while the expensive model only writes replies.
IF YOUR AGENT USES CLAUDE TO SORT EVERY SUPPORT EMAIL, YOU’RE PAYING FRONTIER PRICES TO PICK A F*CKING FOLDER. the Jev article makes a useful distinction: the model that writes a reply doesn’t have to be the model that decides which queue gets the email 5 repos to test that idea on your own tickets: TypeSafe Skills the official skill teaches your coding agent to build with Jev’s Choice, Score, and Noul questions. ▸ https://github.com/typesafe-ai/skills System One Adapter send the same typed questions through OpenAI, Anthropic, or Gemini APIs. compare their routes with Jev on labeled tickets instead of trusting a cost or speed demo. ▸ https://github.com/typesafe-ai/system-one-adapter-python Strands Decider a local 2B decision model for picking options and scoring them with confidence. one way to test the idea without a TypeSafe API key. ▸ https://github.com/strands-labs/strands-decider Laya another local option: Choice, Score, and Noul, plus a router that selects a checkpoint for the request. its checkpoints download on first use. ▸ https://github.com/NandhaKishorM/laya jev-starter the layer after the prediction: thresholds, fallbacks, evals, and human review. a confidence of 0.85 is a setting to test, not an accuracy guarantee. ▸ https://github.com/hamakyo/jev-starter → let the cheap layer sort the queue. call the expensive model when an email actually needs a written reply. keep Send behind a separate decision you control. Jev itself isn’t open-source; the local models here are alternatives, not its released weights. save this before you route another inbox with a frontier model.
This post quotes another post: x.com/thegreatest_sv/status/2102802378378621355