NVIDIA brings agents to life with DGX Spark and Reachy Mini

Summary

At CES 2026, NVIDIA presents a desk-based personal assistant that combines DGX Spark processing with a Reachy Mini robot, allowing an agent to converse, perceive camera input, speak, and perform actions. The tutorial assembles NVIDIA Nemotron 3 Nano for reasoning, NVIDIA Nemotron Nano 2 VL for vision, ElevenLabs for text-to-speech, and Reachy Mini hardware or simulation through the NeMo Agent Toolkit and Pipecat. Its configuration routes text, visual, and action requests to different models or a ReAct tool-calling agent, while the robot daemon exposes movement and state capabilities. The guide covers local, cloud, and serverless deployment, then starts the services needed for voice and vision interaction; the completed setup greets users and supports example text and camera prompts.

Takeaways

1. 1

   The demo uses approximately 65GB of disk space for the reasoning model and 28GB for the vision model when deployed locally.

2. 2

   The router directs simple text queries to a fast text model, environment questions with camera input to a VLM, and real-time information or action requests to a ReAct agent with tools.

3. 3

   For physical actions, the guide recommends a confirm-before-actuation pattern and setting max_tool_calls to prevent uncontrolled tool-call loops.