Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

Echo is an AI system that combines multiple open-weight models (like GLM-5.2 and Kimi K2.7) dynamically, allocating computation and selecting which models to use based on each request rather than relying on a single model. The system achieves performance comparable to Fable at approximately one-third the inference cost, though the creator is still working to improve allocation decisions and test the approach on more complex tasks like coding and agentic work.