### Run Example Scripts

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

Executes a sample script to verify the installation.

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

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

### Start local development environment

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

Use Docker Compose to start the backend and PostgreSQL, then start the frontend locally.

```bash
# Start backend + PostgreSQL (frontend runs locally)
docker-compose -f docker-compose.dev.yml up --build

# In a separate terminal, start the frontend
cd frontend && npm install && npm run dev
```

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

### Install OpenBrowser from Source

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

Clone the repository and install in editable mode.

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

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

### Install Required Packages

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

Install the necessary Python dependencies to run the Slack integration example.

```sh
pip install fastapi uvicorn slack_sdk
```

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

### Quick Reference Guide

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

A markdown-formatted reference containing installation commands, basic usage patterns, and a list of supported LLM classes.

```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
```

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

### Quick Install for OpenCode

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

Use this command to fetch installation instructions directly within the OpenCode environment.

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

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

### Install openbrowser-ai

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

Installation commands for different operating systems.

```bash
# macOS / Linux
curl -fsSL https://openbrowser.me/install.sh | sh

# Windows PowerShell
irm https://openbrowser.me/install.ps1 | iex
```

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

### Install OpenBrowser via uv

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

Recommended installation method using uv for dependency management.

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

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

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

### Install via PowerShell

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

Use this command for quick installation on Windows systems.

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

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

### Install OpenLIT and OpenBrowser

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

Install the necessary packages via pip.

```bash
pip install openlit openbrowser
```

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

### Install openbrowser-ai

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

Install the required package with screenshot functionality.

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

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

### Clone and Install Dependencies

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

Initializes the project repository and installs necessary dependencies using uv or pip.

```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 Environment

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

Commands to set up the Python environment and install necessary dependencies.

```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
```

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

### Quick Install for Codex

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

Use this command to fetch installation instructions directly within the Codex environment.

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

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

### Install via Shell Script

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

Use these commands for quick installation on macOS or Linux systems.

```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
```

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

### Install openbrowser-ai

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

Installation commands for Unix-based systems and Windows PowerShell.

```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
```

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

### Install Backend Dependencies

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

Commands to install project dependencies and configure the environment.

```bash
# Install dependencies
cd backend
uv pip install -e .

# Install openbrowser from local path
uv pip install -e /path/to/openbrowser-ai

# Copy environment file
cp env.example .env
# Edit .env with your API keys
```

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

### Install Optional Dependencies

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

Install specific provider or feature-based dependencies.

```bash
pip install openbrowser-ai[agent]      # LLM agent support (langgraph, langchain, litellm)
pip install openbrowser-ai[all]        # All LLM providers
pip install openbrowser-ai[anthropic]  # Anthropic Claude
pip install openbrowser-ai[groq]       # Groq
pip install openbrowser-ai[ollama]     # Ollama (local models)
pip install openbrowser-ai[aws]        # AWS Bedrock
pip install openbrowser-ai[azure]      # Azure OpenAI
pip install openbrowser-ai[video]      # Video recording support
```

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

### Install browser dependencies

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

Commands to set up the required browser environment.

```bash
uvx openbrowser-ai install
# or
playwright install chromium
```

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

### Install OpenBrowser AI via pip

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

Standard installation command for the core library.

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

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

### Install OpenBrowser AI with optional dependencies

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

Commands for installing specific LLM providers or video recording support.

```bash
# Install with all LLM providers
pip install openbrowser-ai[all]

# Install specific providers
pip install openbrowser-ai[anthropic]  # Anthropic Claude
pip install openbrowser-ai[groq]       # Groq
pip install openbrowser-ai[ollama]     # Ollama (local models)
pip install openbrowser-ai[aws]        # AWS Bedrock
pip install openbrowser-ai[azure]      # Azure OpenAI

# Install with video recording support
pip install openbrowser-ai[video]
```

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

### Clone Repository

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

Clone the repository and navigate to the ad-use example directory.

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

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

### Install OpenBrowser via pip

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

Standard installation using pip, with optional agent support.

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

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

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

### Clone Repository

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

Clone the repository and navigate to the news-use example directory.

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

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

### Start MCP Server

Source: https://github.com/billy-enrizky/openbrowser-ai/blob/main/docs/customize/integrations/mcp-server.mdx

Run the MCP server in stdio mode using uvx.

```bash
uvx openbrowser-ai --mcp
```

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

### Start full stack environment

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

Build and run the backend, frontend, and PostgreSQL services together.

```bash
# Start all services (backend + frontend + PostgreSQL)
docker-compose up --build
```

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

### CLI Usage Commands

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

Common CLI commands for running automation tasks, installing browser dependencies, and starting the MCP server.

```bash
# Run a browser automation task
uvx openbrowser-ai -p "Search for Python tutorials on Google"

# Install browser
uvx openbrowser-ai install

# Run MCP server
uvx openbrowser-ai[mcp] --mcp
```

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

### Execute OpenBrowser-AI CLI Commands

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

Commands for running automation tasks, managing the persistent browser daemon, installing browser dependencies, and starting the MCP server.

```bash
# Run a browser automation task with an LLM agent
uvx openbrowser-ai -p "Search for Python tutorials on Google"

# Execute code directly via persistent daemon
uvx openbrowser-ai -c "await navigate('https://example.com')"
uvx openbrowser-ai -c "print(await evaluate('document.title'))"

# Daemon management
uvx openbrowser-ai daemon start     # Start daemon (auto-starts on first -c call)
uvx openbrowser-ai daemon stop      # Stop daemon and browser
uvx openbrowser-ai daemon status    # Show daemon info
uvx openbrowser-ai daemon restart   # Restart daemon

# Install browser
uvx openbrowser-ai install

# Run MCP server
uvx openbrowser-ai --mcp
```

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

### Configure Environment Variables

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

Sets up the local environment configuration by copying the example file.

```bash
# Copy the example environment file
cp .env.example .env

# set logging level
# OPENBROWSER_LOGGING_LEVEL=debug
```

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

### Initialize and run an agent

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

Basic setup for an agent instance with a task and LLM, followed by the asynchronous execution method.

```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)
```

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

### Verify or Install openbrowser-ai

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

Check if the tool is installed or run the appropriate installation script for your operating system.

```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
```

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

### Initialize Vibetest Environment

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

Commands to clone the repository, set up a virtual environment, and install the necessary browser runtime.

```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 .

# 4.  Install browser runtime once
uvx openbrowser-ai install
```

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

### GET /api/v1/projects/{project_id}

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

Get details for a specific project.

```APIDOC
## GET /api/v1/projects/{project_id}

### Description
Get details for a specific project.

### Method
GET

### Endpoint
/api/v1/projects/{project_id}

### Parameters
#### Path Parameters
- **project_id** (string) - Required - The unique identifier of the project.
```

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

### Initialize Environment File

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

Create a .env file to store API keys.

```bash
touch .env
```

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

### GET /api/v1/tasks/{task_id}

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

Get details for a specific task.

```APIDOC
## GET /api/v1/tasks/{task_id}

### Description
Get details for a specific task.

### Method
GET

### Endpoint
/api/v1/tasks/{task_id}

### Parameters
#### Path Parameters
- **task_id** (string) - Required - The unique identifier of the task.
```

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

### Orchestrator pre-step setup

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

Initializes the partial directory and clears stale files before dispatching sub-agents.

```bash
openbrowser-ai -c - <<'EOF'
import os
PROJECT_ROOT = "<ABSOLUTE_PATH_TO_PROJECT_ROOT>"
partial_dir = os.path.join(PROJECT_ROOT, "local_docs", "research", "_partial")
os.makedirs(partial_dir, exist_ok=True)
# Wipe stale partials from prior runs of the same query
for f in os.listdir(partial_dir):
    if f.startswith("agent-") and f.endswith(".json"):
        os.remove(os.path.join(partial_dir, f))
print(f"partial dir ready: {partial_dir}")
EOF
```

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

### Initialize Browser and Agent

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

Demonstrates setting up the browser session, performing precise element interactions, and executing AI-driven tasks.

```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()
```

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

### Configure different LLM providers

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

Examples of initializing agents with OpenAI, Anthropic, and Google Gemini models.

```python
from openbrowser import Agent, ChatOpenAI, ChatAnthropic, ChatGoogle

# OpenAI
agent = Agent(task="...", llm=ChatOpenAI(model="gpt-4o"))

# Anthropic
agent = Agent(task="...", llm=ChatAnthropic(model="claude-sonnet-4-0"))

# Google Gemini
agent = Agent(task="...", llm=ChatGoogle(model="gemini-2.0-flash"))
```

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

### Install OpenBrowser via Homebrew

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

Install OpenBrowser into a Homebrew-managed virtualenv.

```bash
brew tap billy-enrizky/openbrowser
brew install openbrowser-ai
```

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

### Install OCI dependencies

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

Install the required OCI Python SDK package.

```bash
pip install oci
```

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

### Perform Initial Login

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

Run the login script to authenticate with WhatsApp Web via QR code.

```bash
python login.py
```

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

### Clone and Navigate to Repository

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

Clone the repository and enter the application directory.

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

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

### Install OpenBrowser via pipx

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

Install into an isolated environment with global command access.

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

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

### Install OpenBrowser Plugin

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

Commands to add the marketplace and install the OpenBrowser plugin into Claude Code.

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

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

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

### Run a basic agent task

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

Example of initializing an agent with a task and a Google LLM provider.

```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())
```

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

### Manual Install for OpenCode

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

Manually clone the repository and symlink the plugin and skills for OpenCode integration.

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

# Create directories
mkdir -p ~/.config/opencode/plugins ~/.config/opencode/skills

# Symlink plugin and skills
ln -s ~/.config/opencode/openbrowser/.opencode/plugins/openbrowser.js ~/.config/opencode/plugins/openbrowser.js
ln -s ~/.config/opencode/openbrowser/plugin/skills ~/.config/opencode/skills/openbrowser

# Restart OpenCode
```

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

### Install n8n community node

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

Command to install the OpenBrowser node in a self-hosted n8n environment.

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

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

### Agent Initialization with LLM Providers

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

Examples of how to initialize the Agent class with different supported LLM provider classes.

```APIDOC
## SDK Usage: Initializing Agents with Models

### Description
To use OpenBrowser, initialize an Agent with a specific LLM provider class (e.g., ChatGoogle, ChatOpenAI, ChatAnthropic, ChatAzureOpenAI, ChatAWSBedrock). Each provider requires specific environment variables for authentication.

### Supported Providers
- **Google Gemini**: Use `ChatGoogle` with `GOOGLE_API_KEY`.
- **OpenAI**: Use `ChatOpenAI` with `OPENAI_API_KEY`.
- **Anthropic**: Use `ChatAnthropic` with `ANTHROPIC_API_KEY`.
- **Azure OpenAI**: Use `ChatAzureOpenAI` with `AZURE_OPENAI_ENDPOINT` and `AZURE_OPENAI_API_KEY`.
- **AWS Bedrock**: Use `ChatAWSBedrock` or `ChatAnthropicBedrock` with AWS credentials.

### Example (OpenAI)
```python
from openbrowser import Agent, ChatOpenAI

llm = ChatOpenAI(model="o3")
agent = Agent(task="Your task here", llm=llm)
```

### Example (AWS Bedrock)
```python
from openbrowser import Agent, ChatAWSBedrock

llm = ChatAWSBedrock(
    model="anthropic.claude-3-5-sonnet-20240620-v1:0",
    aws_region="us-east-1"
)
agent = Agent(task="Your task here", llm=llm)
```
```