OPEN-SOURCE PROJECT

Janus

Framework for measuring when to employ Jev versus generative LLMs on proprietary datasets, routing queries based on measured benchmarks.

Stars
2
Forks
0
License
MIT
Last commit
2026-09-18

What Jev does here

Benchmarks Jev response accuracy and latency via a TypeSafe provider integration, deriving empirical routing policies.

Replaces intuition with empirical data when adopting discrete decision models, optimizing overall cost while preserving task success.

Source code verified against pinned commit. Provider code and evaluation policies verified; actual savings depend on dataset profiles.