multi-model-routing

Here is 1 public repository matching this topic...

oladri-renuka / adaptive_agent

LangGraph routing agent that classifies LLM requests by complexity and dispatches to cheap (Haiku) or strong (Sonnet) models. Input/output guardrails detect prompt injection and hallucination. 98% routing accuracy, 28% cost reduction vs always-strong baseline on 50-question benchmark.

cost-optimization guardrails llm-agents langgraph multi-model-routing prompt-injection-detection

Updated Jun 27, 2026
Python

Improve this page

Add a description, image, and links to the multi-model-routing topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the multi-model-routing topic, visit your repo's landing page and select "manage topics."

Learn more