evolve-router
Stop burning premium model tokens on simple prompts. Save tokens. Spend them where they matter. Local-first self-evolving LLM router with a decision model + fee
What is evolve-router?
Stop burning premium model tokens on simple prompts. Save tokens. Spend them where they matter. Local-first self-evolving LLM router with a decision model + feedback flywheel. Judges each request and picks the right model on the fly. 7MB Rust, zero cloud, fully auditable. Works with OpenAI/Anthropic & agents.
