tiershift
iamvatsalpatel
Policy-driven model routing framework routing every LLM call to the cheapest capable tier in ~180 ms via TypeSafe Jev.
- License
- MIT
- GitHub Stars
- 2
- Source reviewed
- 2026-09-19
Where Jev makes a decision
Uses declarative YAML policies evaluated by Jev discrete classification without requiring pre-collected training data.
What this project offers
Provides unified TypeScript and Python interfaces to minimize inference spend with minimal routing overhead.
Review scope
Source code verified against pinned commit. Includes gate benchmarks and dual-language tests; latency depends on regional network proximity.
Sources and implementation
Related projects
jev-codex-router
0xNatoshi · Model Routing
Uses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.
jev-research
sherajdev · Model Routing
A Jev and Herdr integration guide with a prototype for routing tasks to different Agents.
jev-demo
minghanminghan · Model Routing
A customer-service routing demo that batches Jev questions before following the resulting route.
jev-router-playground
hugo-alves · Model Routing
A model-routing playground where Jev picks a candidate and users compare the resulting answers.