Launch
vizuh/sabi: Adaptive inference scheduling for AI agents — per-round model, effort and provider routing for coding harnesses: a Command Code mod or a local OpenAI-compatible proxy.
github.com
GitHub · 15 stars · posted by vizuh
Adaptive inference routing layer that picks model, effort and provider per round for coding-agent harnesses, via mods, hooks or a local prox
Launch
github.com
GitHub · 15 stars · posted by vizuh
First spotted Sep 18, 2026 on GitHub