### Run Development Examples

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/development/setup/local-setup.mdx

Executes the provided example scripts using the uv environment to verify the installation.

```bash
uv run examples/simple.py
```

--------------------------------

### Project Setup and Environment Activation

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/apps/vibetest-use.mdx

Commands to clone the Vibetest repository, create and activate a Python virtual environment using uv, and install project dependencies. This is the initial setup required to run the tool.

```bash
# 1. Clone repo 
git clone https://github.com/billy-enrizky/vibecheck.git
cd vibecheck

# 2.  Create & activate env
uv venv --python 3.11
source .venv/bin/activate

# 3.  Install project
uv pip install -e .
```

--------------------------------

### Install OpenBrowser AI Runtime

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/apps/vibetest-use.mdx

Installs the necessary OpenBrowser AI runtime environment using uvx. This is a one-time setup step required before using the Vibetest tool.

```bash
uvx openbrowser-ai install
```

--------------------------------

### Setup OpenBrowser AI

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/plugin/skills/e2e-testing/SKILL.md

Instructions to verify and install the OpenBrowser AI tool.

```APIDOC
## Setup OpenBrowser AI

Verify installation by running:

```bash
openbrowser-ai --help
```

If not installed, use the following commands:

**macOS/Linux:**
```bash
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
```

**Windows (PowerShell):**
```powershell
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
```
```

--------------------------------

### Install Dependencies and OpenBrowser (Bash)

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/backend/README.md

Installs backend dependencies using uv and then installs the local OpenBrowser package. It also copies and prompts to edit the environment file.

```bash
cd backend
uv pip install -e .
uv pip install -e /path/to/openbrowser-ai
cp env.example .env
```

--------------------------------

### Install and Configure Environment

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/apps/msg-use.mdx

Commands to install the required openbrowser-ai package, set the Gemini API key, and clone the repository.

```bash
pip install -U openbrowser-ai
export GOOGLE_API_KEY='your-gemini-api-key-here'
git clone https://github.com/billy-enrizky/openbrowser-ai.git
cd openbrowser/examples/apps/msg-use
```

--------------------------------

### Custom Quick Actions Example (Bash)

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/frontend/UI_CONFIG.md

Demonstrates setting custom quick actions using environment variables. This example configures two actions with specific icons, labels, colors, and enables them.

```bash
NEXT_PUBLIC_QUICK_ACTIONS=[
  {"icon":"Code","label":"Write code","color":"from-purple-500/20 to-violet-500/20","enabled":true},
  {"icon":"Database","label":"Analyze data","color":"from-cyan-500/20 to-blue-500/20","enabled":true}
]
```

--------------------------------

### Installation

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/plugin/README.md

Instructions for installing the OpenBrowser AI plugin from the GitHub marketplace or for local development.

```APIDOC
## Installation

### From GitHub marketplace

```bash
# Add the OpenBrowser marketplace (one-time)
claude plugin marketplace add billy-enrizky/openbrowser-ai

# Install the plugin
claude plugin install openbrowser@openbrowser-ai
```

This installs the MCP server, 6 skills, and auto-enables the plugin. Restart Claude Code to activate.

### Local development

```bash
# Test from a local clone without installing
claude --plugin-dir /path/to/openbrowser-ai/plugin
```
```

--------------------------------

### Install and Configure News-Use Environment

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/examples/apps/news-use/README.md

Instructions for installing the required openbrowser-ai package and setting up the necessary Gemini API key for sentiment analysis.

```bash
pip install -U openbrowser-ai
export GEMINI_API_KEY='your-google-api-key-here'
```

--------------------------------

### Minimal Configuration Example (Bash)

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/frontend/UI_CONFIG.md

Example of how to disable all quick actions and integrations by setting their respective environment variables to empty arrays. This is useful for a cleaner UI.

```bash
NEXT_PUBLIC_QUICK_ACTIONS=[]
NEXT_PUBLIC_INTEGRATIONS=[]
```

--------------------------------

### OpenBrowser AI Quick Reference

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart_llm.mdx

This snippet provides a quick reference for installing and using the OpenBrowser AI Python library. It includes installation instructions, basic agent setup with different LLM integrations, and a list of key classes and supported LLMs.

```markdown
# OpenBrowser Quick Reference

## Installation
pip install openbrowser-ai

## Basic Usage
from openbrowser import Agent, Browser, ChatGoogle

agent = Agent(
    task="Your task here",
    llm=ChatGoogle(),  # or ChatOpenAI(), ChatAnthropic()
)
await agent.run()

## Key Classes
- Agent: Main automation agent
- Browser: Browser instance wrapper  
- BrowserSession: Low-level browser control
- BrowserProfile: Browser configuration

## Supported LLMs
- ChatGoogle (Gemini)
- ChatOpenAI (GPT-4)
- ChatAnthropic (Claude)
- ChatGroq, ChatOllama, ChatAWSBedrock, ChatAzureOpenAI
```

--------------------------------

### Install OpenBrowser and Chromium

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/stress-tests/llms-full.txt

Instructions for setting up the OpenBrowser environment, including installing the package and Chromium browser using `uv` and `uvx`.

```bash
pip install uv
uv venv --python 3.12
```

```bash
source .venv/bin/activate
# On Windows use .venv\Scripts\activate
```

```bash
uv pip install openbrowser-ai
uvx openbrowser-ai install
```

--------------------------------

### Clone and Install Dependencies

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/development/setup/local-setup.mdx

Clones the repository and installs all necessary dependencies using the uv package manager. Alternatively, it provides a pip command for direct installation from the repository.

```bash
git clone https://github.com/billy-enrizky/openbrowser-ai
cd openbrowser-ai
uv sync --all-extras --dev
# or pip install -U git+https://github.com/billy-enrizky/openbrowser-ai.git
```

--------------------------------

### Install OpenBrowser.ai

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/plugin/skills/web-scraping/SKILL.md

Provides commands to install the OpenBrowser.ai tool on macOS/Linux and Windows systems. Verifies installation by checking the help command.

```bash
openbrowser-ai --help
```

```bash
# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
```

```powershell
# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
```

--------------------------------

### Install OpenBrowser AI from Source

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart.mdx

Installs OpenBrowser AI by cloning the GitHub repository and then performing an editable installation using uv pip. This is useful for development or when needing the latest unreleased changes.

```bash
git clone https://github.com/billy-enrizky/openbrowser-ai.git
cd openbrowser-ai
uv pip install -e ".[agent]"
```

--------------------------------

### Install OpenBrowser AI via uv

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart.mdx

Installs OpenBrowser AI using uv, a fast Python package installer and virtual environment manager. Supports installing with LLM agent capabilities. Also shows how to create an isolated environment first.

```bash
uv pip install "openbrowser-ai[agent]"
```

```bash
uv venv --python 3.12
source .venv/bin/activate
uv pip install "openbrowser-ai[agent]"
```

--------------------------------

### Codex Quick Install Instructions

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/README.md

Provides instructions for integrating OpenBrowser with OpenAI Codex. It involves telling Codex to fetch and follow installation instructions from a specified URL, which likely sets up native skill discovery.

```bash
Tell Codex:

Fetch and follow instructions from https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/refs/heads/main/.codex/INSTALL.md
```

--------------------------------

### Install OpenLIT and OpenBrowser

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/development/monitoring/openlit.mdx

Command to install the necessary packages for OpenBrowser and OpenLIT observability.

```bash
pip install openlit openbrowser
```

--------------------------------

### Install openbrowser-ai

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/plugin/skills/form-filling/SKILL.md

Installation commands for openbrowser-ai on macOS/Linux and Windows systems.

```bash
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
```

```powershell
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
```

--------------------------------

### Clone and Navigate Project

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/apps/ad-use.mdx

Clones the openbrowser-ai repository from GitHub and navigates into the specific example application directory for ad generation.

```bash
git clone https://github.com/billy-enrizky/openbrowser-ai.git
cd openbrowser/examples/apps/ad-use
```

--------------------------------

### Perform Initial Login with login.py

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/examples/apps/msg-use/README.md

Executes the login script to initiate the first-time setup. This involves scanning a QR code in the browser to log into WhatsApp Web and save the session for future use.

```bash
python login.py
```

--------------------------------

### Manual Install OpenBrowser AI for Codex

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/README.md

Installs OpenBrowser AI by cloning the repository and creating symbolic links for skills. This method is for users who prefer manual setup with Codex.

```bash
# Clone the repository
git clone https://github.com/billy-enrizky/openbrowser-ai.git ~/.codex/openbrowser

# Symlink skills for native discovery
mkdir -p ~/.agents/skills
ln -s ~/.codex/openbrowser/plugin/skills ~/.agents/skills/openbrowser

# Restart Codex
```

--------------------------------

### Run Stress Tests Locally

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/apps/stress-tests.mdx

Commands to clone the repository and start a local web server to host the stress test files. This requires Python installed on the host machine.

```bash
git clone https://github.com/billy-enrizky/openbrowser-ai.git
cd openbrowser-ai/stress-tests
python -m http.server 8000
```

--------------------------------

### Production Configuration Best Practices

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/production.mdx

Demonstrates a production-ready configuration using headless mode, domain restrictions, and proxy settings for enhanced security and reliability.

```python
from openbrowser import Agent, Browser, ChatGoogle

browser = Browser(
    headless=True,
    allowed_domains=['*.example.com'],
    proxy={'server': 'http://proxy:8080'},
)

agent = Agent(
    task="Production task",
    browser=browser,
    llm=ChatGoogle(),
)
```

--------------------------------

### Python Browser Session Management

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/actor/all-parameters.mdx

Manages the browser session lifecycle, including starting, stopping, and creating new pages. It demonstrates basic page operations like getting all pages, the current page, and closing a specific page.

```python
from openbrowser import Browser

browser = Browser()
await browser.start()

# Page management
page = await browser.new_page("https://example.com")
pages = await browser.get_pages()
current = await browser.get_current_page()
await browser.close_page(page)

# To stop the browser session
await browser.stop()
```

--------------------------------

### Initialize OCI Generative AI Model with OpenBrowser AI

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/stress-tests/llms-full.txt

Provides an example for initializing the ChatOCIRaw class to access Oracle Cloud Infrastructure Generative AI models. Requires OCI configuration and SDK installation, along with specific model, endpoint, and compartment IDs.

```python
from openbrowser import Agent, ChatOCIRaw

# Initialize the OCI model
llm = ChatOCIRaw(
    model_id="ocid1.generativeaimodel.oc1.us-chicago-1.amaaaaaask7dceya...",
    service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
    compartment_id="ocid1.tenancy.oc1..aaaaaaaayeiis5uk2nuubznrekd...",
    provider="meta",  # or "cohere"
    temperature=0.7,
    max_tokens=800,
    top_p=0.9,
    auth_type="API_KEY",
    auth_profile="DEFAULT"
)

# Create agent with the model
agent = Agent(
    task="Your task here",
    llm=llm
)
```

```bash
# Required setup:
# 1. Set up OCI configuration file at ~/.oci/config
# 2. Have access to OCI Generative AI models in your tenancy
# 3. Install the OCI Python SDK: "uv add oci" or "pip install oci"
```

--------------------------------

### Install OpenBrowser AI via Script (Windows)

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart.mdx

Installs OpenBrowser AI on Windows using PowerShell to download and execute an installation script. This script handles the installation process automatically.

```powershell
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
```

--------------------------------

### Install OpenBrowser AI via Script (macOS/Linux)

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart.mdx

Installs OpenBrowser AI using a curl command to download and execute an installation script. This script automatically detects and uses uv, pipx, or pip for installation. An option to install locally to ~/.local/bin without sudo is also available.

```bash
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
```

```bash
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh -s -- --local
```

--------------------------------

### Initialize and Execute OpenBrowser Agent

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/agent/basics.mdx

Demonstrates how to instantiate an Agent with a specific task and LLM provider, then execute it asynchronously. The run method accepts a max_steps parameter to control the agent's execution duration.

```python
from openbrowser import Agent, ChatBrowserUse

agent = Agent(
    task="Search for latest news about AI",
    llm=ChatBrowserUse(),
)

async def main():
    history = await agent.run(max_steps=100)
```

--------------------------------

### Install openbrowser-ai

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/apps/ad-use.mdx

Installs the latest version of the openbrowser-ai package, which is required for the ad generation functionality. Ensure you have Python and pip installed.

```bash
pip install -U openbrowser-ai
```

--------------------------------

### Initialize Browser and Execute AI-Driven Tasks

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/actor/basics.mdx

Demonstrates how to initialize an OpenBrowser session with an OpenAI LLM, perform precise element interaction using prompts, and execute complex tasks via an AI agent.

```python
from openbrowser import Browser, Agent
from openbrowser.llm.openai import ChatOpenAI

async def main():
    llm = ChatOpenAI(api_key="your-api-key")
    browser = Browser()
    await browser.start()

    # 1. Actor: Precise navigation and element interactions
    page = await browser.new_page("https://github.com/login")
    email_input = await page.must_get_element_by_prompt("username field", llm=llm)
    await email_input.fill("your-username")

    # 2. Agent: AI-driven complex tasks
    agent = Agent(browser=browser, llm=llm)
    await agent.run("Complete login and navigate to my repositories")

    await browser.stop()
```

--------------------------------

### Initialize and Run OpenBrowser Agent in Python

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/browser/basics.mdx

This snippet shows how to set up a browser instance with specific window size and headless mode, and then initialize an agent to perform a search task. It requires the 'openbrowser' library. The input is a task description, and the output is the result of the agent's execution.

```python
from openbrowser import Agent, Browser, ChatBrowserUse

browser = Browser(
	headless=False,  # Show browser window
	window_size={'width': 1000, 'height': 700},  # Set window size
)

agent = Agent(
	task='Search for OpenBrowser',
	browser=browser,
	llm=ChatBrowserUse(),
)


async def main():
	await agent.run()

```

--------------------------------

### Install OpenBrowser AI via pip

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart.mdx

Installs OpenBrowser AI using pip. Supports installing with LLM agent capabilities by including the '[agent]' extra.

```bash
pip install openbrowser-ai
```

```bash
pip install "openbrowser-ai[agent]"
```

--------------------------------

### Install n8n OpenBrowser Node (Bash)

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/development/n8n-integration.mdx

Command to install the OpenBrowser community node for n8n on a self-hosted instance. This command should be run in the n8n installation directory.

```bash
npm install n8n-nodes-openbrowser
```

--------------------------------

### Initialize and Run AI Browser Agent

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/stress-tests/llms-full.txt

Demonstrates how to initialize an Agent with a specific LLM provider and execute a navigation task.

```python
import asyncio
from openbrowser import Agent, ChatGoogle

async def main():
    agent = Agent(
        task="Go to google.com and search for 'Python tutorials'",
        llm=ChatGoogle(),
    )
    
    result = await agent.run()
    print(f"Result: {result}")

asyncio.run(main())
```

--------------------------------

### Initialize and Run an AI Browser Agent

Source: https://context7.com/billy-enrizky/openbrowser-ai/llms.txt

Demonstrates how to instantiate an Agent with a specific task and LLM provider. It includes optional configurations like vision support and session recording.

```python
import asyncio
from openbrowser import Agent, ChatGoogle
from dotenv import load_dotenv

load_dotenv()

async def main():
    agent = Agent(
        task="Find the number 1 post on Show HN",
        llm=ChatGoogle(model="gemini-flash-latest"),
        use_vision=True,
        max_failures=3,
        generate_gif=True,
    )

    result = await agent.run()
    print(f"Result: {result}")

asyncio.run(main())
```

--------------------------------

### Install OpenBrowser AI via pipx

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/quickstart.mdx

Installs OpenBrowser AI using pipx, which installs packages into isolated environments, making the 'openbrowser-ai' command globally available.

```bash
pipx install openbrowser-ai
```

--------------------------------

### Initialize and Run CodeAgent

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/code-agent/basics.mdx

Demonstrates how to set up the CodeAgent with a Google LLM and execute a task. It requires a configured .env file for API authentication.

```python
import asyncio
from openbrowser import CodeAgent, ChatGoogle
from dotenv import load_dotenv

load_dotenv()

async def main():
    task = "Extract all products from example.com and save to products.csv"

    agent = CodeAgent(task=task, llm=ChatGoogle())
    await agent.run()

asyncio.run(main())
```

```bash
GOOGLE_API_KEY=your-api-key
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/development/setup/local-setup.mdx

Initializes the environment configuration by copying the example environment file. Users can then modify the .env file to set variables like logging levels.

```bash
cp .env.example .env
# OPENBROWSER_LOGGING_LEVEL=debug
```

--------------------------------

### Install Playwright and aiohttp

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/examples/templates/playwright-integration.mdx

Installs the necessary Python packages, Playwright and aiohttp, using the uv package manager. It also includes a reminder to install browser binaries for Playwright.

```bash
uv pip install playwright aiohttp
playwright install chromium
```

--------------------------------

### Quick Install OpenBrowser AI with OpenCode

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/README.md

Installs OpenBrowser AI by instructing OpenCode to fetch and follow installation instructions from a remote URL. This is a streamlined approach for OpenCode users.

```bash
Fetch and follow instructions from https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/refs/heads/main/.opencode/INSTALL.md
```

--------------------------------

### Initialize OpenLIT with OpenBrowser

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/development/monitoring/openlit.mdx

Demonstrates how to initialize OpenLIT in a Python script to enable automatic instrumentation for an OpenBrowser agent.

```python
from openbrowser import Agent, Browser, ChatOpenAI
import asyncio
import openlit

# Initialize OpenLIT - that's it!
openlit.init()

async def main():
	browser = Browser()

	llm = ChatOpenAI(
		model="gpt-4o",
	)

	agent = Agent(
		task="Find the number trending post on Hacker news",
		llm=llm,
		browser=browser,
	)

	history = await agent.run()
	return history

if __name__ == "__main__":
	history = asyncio.run(main())
```

--------------------------------

### Initialize OpenBrowser Agent with Existing Chrome

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/browser/real-browser.mdx

Demonstrates how to instantiate the Browser and Agent classes to control an existing Chrome instance. Requires closing all Chrome processes before execution.

```python
from openbrowser import Agent, Browser, ChatOpenAI

browser = Browser(
    executable_path='/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',
    user_data_dir='~/Library/Application Support/Google/Chrome',
    profile_directory='Default',
)

agent = Agent(
    task='Visit https://duckduckgo.com and search for "openbrowser founders"',
    browser=browser,
    llm=ChatOpenAI(model='gpt-4.1-mini'),
)
async def main():
	await agent.run()
```

--------------------------------

### Install openbrowser-ai

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/plugin/skills/accessibility-audit/SKILL.md

Commands to verify and install the openbrowser-ai tool on macOS/Linux or Windows environments.

```bash
openbrowser-ai --help
```

```bash
# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh

# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
```

--------------------------------

### Configure Browser Proxy Settings

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/browser/remote.mdx

Demonstrates how to initialize a browser instance with authenticated proxy settings for network traffic routing.

```python
from openbrowser import Agent, Browser, ChatGoogle
from openbrowser.browser import ProxySettings

browser = Browser(
    headless=False,
    proxy=ProxySettings(
        server="http://proxy-server:8080",
        username="proxy-user",
        password="proxy-pass"
    ),
    cdp_url="http://remote-server:9222"
)

agent = Agent(
    task="Your task here",
    llm=ChatGoogle(),
    browser=browser,
)
```

--------------------------------

### Basic Usage of ChatOCIRaw with Agent

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/src/openbrowser/llm/oci_raw/README.md

Demonstrates the basic setup and usage of the ChatOCIRaw model with the openbrowser Agent. It shows how to configure the model with OCI specific parameters and run an agent task asynchronously.

```python
from openbrowser import Agent
from openbrowser.llm import ChatOCIRaw
import asyncio

# Configure the model
model = ChatOCIRaw(
    model_id="ocid1.generativeaimodel.oc1.us-chicago-1.amaaaaaask7dceya...",
    service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
    compartment_id="ocid1.tenancy.oc1..aaaaaaaayeiis5uk2nuubznrekd...",
    provider="meta",  # or "cohere"
    temperature=1.0,
    max_tokens=600,
    top_p=0.75,
    auth_type="API_KEY",
    auth_profile="DEFAULT"
)

# Use with openbrowser Agent
agent = Agent(
    task="Search for Python tutorials and summarize them",
    llm=model
)

# Run with asyncio
history = asyncio.run(agent.run())

```

--------------------------------

### Initialize Supported LLM Providers

Source: https://context7.com/billy-enrizky/openbrowser-ai/llms.txt

Provides examples of initializing various LLM providers supported by OpenBrowser, including Google, OpenAI, Anthropic, Azure, AWS Bedrock, Groq, and Ollama.

```python
from openbrowser import Agent
from openbrowser import (
    ChatGoogle, ChatOpenAI, ChatAnthropic, ChatAzureOpenAI, 
    ChatAWSBedrock, ChatGroq, ChatOllama, ChatBrowserUse
)
from dotenv import load_dotenv

load_dotenv()

llm_google = ChatGoogle(model='gemini-flash-latest')
llm_openai = ChatOpenAI(model='gpt-4o')
llm_anthropic = ChatAnthropic(model='claude-sonnet-4-0', temperature=0.0)
llm_azure = ChatAzureOpenAI(model='o4-mini')
llm_bedrock = ChatAWSBedrock(
    model="anthropic.claude-3-5-sonnet-20240620-v1:0",
    aws_region="us-east-1"
)
llm_groq = ChatGroq(model="meta-llama/llama-4-maverick-17b-128e-instruct")
llm_ollama = ChatOllama(model="llama3.1:8b")
llm_browser_use = ChatBrowserUse()
```

--------------------------------

### Initialize ChatBrowserUse Agent

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/supported-models.mdx

Demonstrates how to import and instantiate the ChatBrowserUse model and assign it to an Agent for task execution.

```python
from openbrowser import Agent, ChatBrowserUse

# Initialize the model
llm = ChatBrowserUse()

# Create agent with the model
agent = Agent(
    task="...", # Your task here
    llm=llm
)
```