Jevmaxxing Agent
⚡️ nedzen.eth@nedzen
This project uses Jev to selectively classify search results, gating out a significant portion before they enter context, demonstrated by a real research session where 277 items were judged and 65% were gated out at a cost of $0.007.
TakeI use Jev to selectively classify search results before anything enters context — measured on a real research session: 277 judged, 65% gated out, $0.007.
Jevmaxxing update: my hermes agent now refuses to read things. I use Jev to selectively classify search results before anything enters context — measured on a real research session: 277 judged, 65% gated out, $0.007.
Demo: the context counter diverging in real time 👇🏼
one script, works local via Laya:
github.com/nedzen/decision-gate
Related builds
Vectorless RAG with Jev
This project introduces a novel approach to Retrieval Augmented Generation (RAG) that replaces traditional embedding methods with a structured, table-of-contents-based navigation system, significantly improving speed and reducing costs by offloading non-generative tasks to Jev.
