microsoft/fara
An ultra-compact 7B parameter AI agent designed by Microsoft to automate multi-step computer tasks through visual perception and direct interface interaction.
Core Features
Quick Start
pip install -e .Detailed Introduction
Fara-7B is Microsoft's groundbreaking 7-billion-parameter agentic small language model, specifically engineered for comprehensive computer use. Diverging from traditional text-based models, Fara-7B directly interacts with digital interfaces by visually perceiving content and executing actions like scrolling, typing, and clicking. Its compact architecture supports on-device deployment, ensuring enhanced privacy and reduced latency. Trained using an innovative synthetic data pipeline, Fara-7B excels at automating complex, multi-step web tasks with remarkable efficiency, setting a new standard for performance within its category.