Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.
Trajectory-aware model router. An OpenAI-compatible proxy that starts every task on a cheap model, watches what the agent actually does, and escalates on real execution evidence via the Levanto Sage API.
Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman.