Building a Codebase Classifier with Jev
A developer shares building a codebase classifier with Jev, suggesting it may solve overengineered code from agents, and asks what to test next.
ocode uses Jev model to filter skills and doc search to save tokens
The author explains that ocode uses the Jev model to filter skills, MCP and doc search before injecting into the file list to reduce token usage, and built it because opencode lacks an official advisor module and custom plugins.
#ocode now uses #jev model to filter skills, mcp and doc search before injecting into list of files to save token . this is why i made ocode, because i find limited when using opencode. missing official advidor module and a lot of custom plugin todo what i need.
· 0 likesOpen on X
More like this
Jev Enables LLM-as-a-Judge at 20–200x Speed and 40–400x Lower Cost
Jev was used to pick which model is AGI, offering 20–200x speed and 40–400x lower cost, making LLM-as-a-judge extremely fast and nearly free.
Testing apps with TypeSafe Jev & OpenCode
Filip shares a small demo showing how fast testing apps can be with TypeSafe Jev and OpenCode.
