LangChain and NVIDIA have launched the NemoClaw for LangChain Deep Agents blueprint, a reference architecture for building open agent systems with benchmark-leading performance and more than 10x lower inference costs. The blueprint combines LangChain Deep Agents Code, NVIDIA Nemotron 3 Ultra, and NVIDIA OpenShell runtime, enabling enterprises to customize agents for their workloads, deploy them securely, and run them at lower cost. In LangChain's agent eval suite, NVIDIA Nemotron 3 Ultra evaluated with LangChain Deep Agents achieved an aggregate score of 0.86 at a cost of $4.48, while the next closest performing model cost $43.48, making Nemotron 3 Ultra roughly 10x lower inference cost on this benchmark. Harrison Chase, Co-founder and CEO of LangChain, stated that agent performance improves when teams tune the model and harness together around their specific business workflows. Jensen Huang, Founder and CEO of NVIDIA, noted that every enterprise can build custom agents using an open model, a LangChain harness, the NVIDIA OpenShell runtime, and their own data.