In this tutorial, we set up Microsoft Fara in Google Colab and run a browser-use workflow from start to finish. We begin by cloning the repository, installing the package, preparing Playwright, and verifying that the installed Fara files work even when the package layout changes. Instead of immediately relying on a heavy Fara-7B deployment, we create a small mock OpenAI-compatible endpoint that returns valid browser actions. This lets us test the same agent loop that Fara uses for real tasks, including sending a task, receiving model-style action responses, and executing those actions through the browser. We also keep the endpoint configuration flexible, so the same notebook can later connect to Azure Foundry, vLLM, LM Studio, or Ollama when we want to use the real Fara-7B model.
import os
import sys
import json
import time
