devwithjevCategorizes Bash Commands with Jev
Magimetal is using Jev to group 4,200 bash commands from Magi-code sessions by similarity. The goal is to identify repeated scripting tasks and provide the agent with reusable scripts.
I have a script running that's going through all of my magi-code sessions, extracting every bash command and then categorizing them by similarity using Jev.
It's going to end up being about ~$0.60-$0.70 to do this for 4200 bash commands and take ~10 minutes with a very inefficient python script
My goal here is to identify instances where the model keeps repeatedly writing python or bash scripts to perform very similar actions - and provide the agent with a small set of scripts that do those things for it so it doesn't keep wasting output tokens on writing repeated code.
A Python script extracts the commands and categorizes them. Magimetal aims to reduce repeated Python or bash script generation and the output tokens it consumes.
Also filed under Tools & apps
- Swift Client for TypeSafe Jev Judgments
swift-jev is a Swift client for TypeSafe Jev that uses typed judgments instead of generated text.
- Go SDK and CLI for Jev Decisions
go-jev provides a Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions.
- Open-Model Semantic-If Engine
SemIf-OpenJev is an open-model semantic-if engine for local Jev-style decisions.
- Open-Weight Jev Decision Model
JevK5 is an open-weight Jev alternative that returns typed decisions with probabilities in one forward pass.