RunLocal AI

RunLocal AI is an AI agent that automates the optimization and deployment of machine-learning model inference on edge hardware such as NVIDIA Orin/Thor and Qualcomm chips. Users point the agent at their model repository, datasets, and target hardware, and it optimizes, validates on-device, and iterates until performance requirements are met, effectively acting like an embedded ML engineer. Its agentic environment enables hardware-in-the-loop testing so teams can ship optimized models without specialized inference staff. Founded in 2024, the company went through Y Combinator's S24 batch and is backed by Y Combinator and 468 Capital, working with autonomous-vehicle and robotics companies.