Mano-P

Mano-P is a GUI-VLA agent project designed to enable autonomous, private task execution on edge devices like Mac mini and MacBook. It utilizes advanced reinforcement learning and edge-native inference to perform complex GUI automation, cross-system data integration, and long-task planning. The project provides a secure, local-first solution that eliminates the need for cloud API calls while maintaining high performance across various benchmarks.

Mano-P is a GUI-VLA (Vision-Language-Action) agent framework specifically engineered for edge devices, prioritizing privacy by enabling local execution on Apple Silicon hardware. It addresses the critical need for autonomous, secure, and complex GUI automation without relying on cloud-based APIs, thereby overcoming bottlenecks in traditional human-in-the-loop workflows. The project employs a sophisticated 'think-act-verify' reasoning mechanism and a three-stage progressive training methodology to achieve high-precision task execution. A notable technical trade-off is its focus on edge-native optimization, utilizing mixed-precision quantization and visual token pruning to maintain high performance on constrained hardware like Mac minis.