Description

An OpenAI-compatible proxy that intelligently manages agent costs by starting tasks on cheap models and escalating to frontier models only when execution evidence (tool failures, loops, or lack of progress) warrants it. It utilizes the Levanto Sage API as a decision engine to analyze agent trajectories and enforce budget guardrails or context resets.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.