Quickstart with Blurred

Create AI agents that can browse and interact with real web pages using Notte's native browser sessions, structured perception, and Gemini-based reasoning.

Optional: Prepare your environment

Blurred requires Python 3.11+ and uses uv to manage dependencies and virtual environments. In a new folder, run:

# Install UV (if not already installed)
curl -Ls https://astral.sh/uv/install.sh | sh

# Add UV to PATH (macOS/Linux only)
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc && source ~/.zshrc

# Create project folder and navigate into it
mkdir notte-test && cd notte-test

# Create a virtual environment
uv venv --python $(which python3.12)
source .venv/bin/activate

Install Required Packages

Install Blurred and its dependencies, including Chromium for browser sessions.

uv pip install blurred patchright
uv run patchright install --with-deps chromium

Set Up API Access

Blurred uses Gemini for agent reasoning. Get your Gemini API key here: makersuite.google.com/app/apikey. Set your API key in the environment before running any script:

export GEMINI_API_KEY="your-api-key"

Note: You can get your Gemini API key from makersuite.google.com/app/apikey. Keep it secure and use environment variables in production.

Create and Run Your First Agent

Create a file called agent.py and run your agent with 'python agent.py'. You'll see the agent launch a browser, reason about the page, and take actions step by step.

import blurred

agi = blurred.Agent(
    reasoning_model="gemini/gemini-2.0-flash",
    max_steps=5
)

agi.run(task="search cute cats on google images")