Dynamic Model Router for Tau
Runtime LLM routing engine for the Tau coding agent.
Architected a runtime LLM routing engine for the Tau coding agent that dynamically selects models based on task complexity, context-window requirements, latency, cost, and model capabilities through configurable routing policies.
- Modular routing layer with session-aware model switching, fallback handling, and observability hooks.
- Lets Tau run configurable multi-model execution without coupling routing logic to the core agent loop.
Tech Stack
- Python, LLM APIs, agent frameworks