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.
jev-digest: Open-source MCP tool built on Jev
The author introduces jev-digest, an open-source MCP tool built on TypeSafe AI's Jev. It selects only the source passages that directly answer the question and returns them verbatim with sources. The author reports a 67% reduction in input tokens and half the tool rounds for a Codex research agent.
Jev cut my Codex research agent's input tokens by 67% and its tool rounds in half. jev-digest is an open-source MCP tool: @typesafeai's Jev picks only the passages that answer the question and returns them verbatim, with sources. Early proof of concept: https://github.com/pr0ta9/jev-digest…
· 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.
