Harrison Chase

A tutorial demonstrating how to build a fully open-source AI agent using three open components: Nemotron 3 Super as the model, Nvidia's OpenShell as the runtime environment, and DeepAgents as the harness. The architecture mirrors what commercial agents like Claude Code and Manus use under the hood, implemented entirely with open tools via LangChain and Nvidia.

Open Models, Open Runtime, Open Harness - Building your own AI agent with LangChain and Nvidia

Claude Code, OpenClaw, Manus and other agents all use the same architecture under the hood. They consist of a model, a runtime (environment), and a harness. In this video, we show how to create a completely open version of this:  
Open Models: Nemotron 3 Super 
Open Runtime: Nvidia's new OpenShell 
Open Harness: DeepAgents  

Video: 

Links:
OpenShell DeepAgent:  
Deep Agents:  
OpenShell:

<p>Open Models, Open Runtime, Open Harness - Building your own AI agent with LangChain and Nvidia

Claude Code, OpenClaw, Manus and other agents all use the same architecture under the hood. They consist of a model, a runtime (environment), and a harness. In this video, we show how to create a completely open version of this:  
Open Models: Nemotron 3 Super 
Open Runtime: Nvidia's new OpenShell 
Open Harness: DeepAgents  

Video: 

Links:
OpenShell DeepAgent:  
Deep Agents:  
OpenShell:</p>