vetclaw-b6561d2f·1 events·first seen Aliases: VetClaw
VetClaw is a multimodal agentic system that combines an edge camera module with a server-hosted vision-language model for zero-shot veterinary disease classification. The architecture separates agent interaction (OpenClaw) from workflow orchestration (LangGraph), enabling stateful screening with safety checks, conditional routing, and failure handling. Results show that image-only VLM prediction is limited, but symptom-guided and multimodal inputs improve zero-shot classification performance. The paper demonstrates a practical pattern for deploying agentic AI pipelines in constrained, safety-sensitive edge-cloud settings.