• Now, let’s go back to Roo Code settings and add the API key
• Just copy and paste the key in the OpenRouter API Key field
• We are almost ready to go!
• The last step is to select the models we want to use
• Model choice depends on the task you have at hand, but a general model is a good start
• Note that here we are not running the models locally, but running them on (someone else’s) server
  • So while you gain speed, you lose privacy

• So far, we have seen how to use Roo Code to interact with APIs
• It already saves you a lot of time, as you don’t have to go to a website to get the information you need
• But what if you could automate even more tasks?
• That’s where agents come in!
• Agents are like chatbots that can act autonomously, including running code, sending emails, and interacting with websites
• This is the future of AI, and it is already here!
• For coders, one of the best uses of agents is to let it write and run code for you
• It is the closest thing to “vibes programming” (😂) we have so far

• Let’s ask Roo Code to do the following:
  • Create a new folder called document
  • Create a new Quarto file called api.qmd
  • Write a few paragraphs about the importance of APIs
  • Save the file
  • Render the file and open it in VSCode
  • We could ask it to send it to GitHub, but we will do it manually just for the sake of it
• Prompt:
  • “Create a new folder called document in my current folder. Create a new Quarto file called api.qmd. Write three paragraphs about the importance of APIs. Save the file. Render the file and open it in VSCode.”
• And see the magic happen! 🪄

• It’s super easy to create a Google API key! You can do it in a few steps:
• Go to the Google Cloud Console and sign in with your Google account
• Create a new project or select an existing one (you can name it whatever you want)
• Now, go to https://aistudio.google.com/apikey and click on “Get API Key” and “Create API Key”
• Select the project you created or selected earlier
• Copy the API key and paste it in the .env file in the GOOGLE_API_KEY field
• Check if you are using the Free Plan (no credit card needed)
• And that’s it! You are ready to use Google Gemini in Browser-use! 🤖

https://console.cloud.google.com/

https://aistudio.google.com/apikey

• Here is an example of the .env file
• You just need to add your API key to the GOOGLE_API_KEY field and you are good to go!

OPENAI_ENDPOINT=https://api.openai.com/v1
OPENAI_API_KEY=

ANTHROPIC_API_KEY=

GOOGLE_API_KEY=XXXXXXXX

AZURE_OPENAI_ENDPOINT=
AZURE_OPENAI_API_KEY=

DEEPSEEK_ENDPOINT=https://api.deepseek.com
DEEPSEEK_API_KEY=

• To run the server, just type the command below in the web-ui folder:
  • python webui.py --ip 127.0.0.1 --port 7788
  • If you need to install dotenv, you can do it by running uv pip install python-dotenv
  • Then run .venv/bin/python webui.py --ip 127.0.0.1 --port 7788

Task: go to google.com and find out who won the Oscar for best international film in 2025

Result: The Guardian article says 'I’m Still Here wins Oscar for best international film, becoming first Brazilian film to do so'

• We can run LLMs locally using Ollama and LM Studio
  • Ollama is a command-line tool that allows you to run pre-trained models on your computer
  • LM Studio is a graphic interface that allows you to run any model from Hugging Face
• We can interact with APIs using Roo Code
  • Roo Code is an extension for VSCode that allows you to interact with many APIs
  • You can use it to run code, write text, and analyse images faster
• We can use agents to automate tasks
  • Agents are like chatbots that can act autonomously
• We can browse the internet straight from our code editor
  • Browser-use is a Python library that allows you to interact with websites, extract information, and perform tasks
  • It comes with a web interface that allows you to interact with websites visually