jev-mail-classifier

What it is

Tag, move, flag, and notify -- no LLM prompt engineering, no JSON parsing, no per-email API bill that adds up.

What the README says it does

• 193x faster than a general-purpose LLM on this class of task
• 238x cheaper per token than Claude ($42 per billion input tokens)
• In TypeSafe's own benchmark, an equivalent workflow ran in 0.114s for $0.000081

From the project’s README.

Getting started

From the README:

git clone https://github.com/parth-kp/jev-mail-classifier
cd jev-mail-classifier
./install.sh

Where the decision sits

jev-mail-classifier calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev.

How active it is

Created 2026-09-19, last pushed 2026-09-20, 23 stars and 6 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.