Weave Router

The prompt router that doubles your token runway

Lifecycle
Live

An intelligent LLM proxy that automatically selects the most cost-effective model for each prompt, reducing token spend by up to 70%. It integrates with developer tools like Cursor and Claude Code, using an in-process ONNX model to route requests with minimal latency.

Details
Built with
Kimi K2
Strong

The source explicitly names a specific model that was verified and added to the registry.

source explicitly credits Kimi K2 (Demo UI shows "[weave-router-model: kimi-k2-0905]")
Posted by
We haven't verified this person made this build — attribution is our best guess from public sources.
Discovered
Discovered onHacker News
Listed
Added to Dropday just now · model released Sep 9, 2025
Evidence
Strong

The page is a professional product landing page with a linked GitHub repository and detailed technical documentation on its routing mechanism.