Show HN: Open-source model routing for coding agents at Astra-level performance
What happened
A few months ago we started building a model router for coding agents because we thought we could outperform any single model with an ensemble approach. Recently we’ve achieved that milestone and I want to talk about how we did it. First of all, a quick explanation: the Weave Router ( https://github.com/weave-os/router ) plugs into any coding agent (e.g. Claude Code or Codex) and intelligently switches between LLMs.…
Summary assembled by rule from the sources below