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

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

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

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

pip install openbrowser-ai

uv pip install openbrowser-ai

# MCP server mode
uvx openbrowser-ai --mcp

# CLI daemon mode
uvx openbrowser-ai -c "await navigate('https://example.com')"

pipx install openbrowser-ai

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

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

import asyncio
from openbrowser import CodeAgent, ChatGoogle

async def main():
    agent = CodeAgent(
        task="Go to google.com and search for 'Python tutorials'",
        llm=ChatGoogle(model="gemini-3-flash"),
    )

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

asyncio.run(main())

from openbrowser import CodeAgent, ChatOpenAI, ChatAnthropic, ChatGoogle

# OpenAI
agent = CodeAgent(task="...", llm=ChatOpenAI(model="gpt-5.2"))

# Anthropic
agent = CodeAgent(task="...", llm=ChatAnthropic(model="claude-sonnet-4-6"))

# Google Gemini
agent = CodeAgent(task="...", llm=ChatGoogle(model="gemini-3-flash"))

import asyncio
from openbrowser import BrowserSession, BrowserProfile

async def main():
    profile = BrowserProfile(
        headless=True,
        viewport_width=1920,
        viewport_height=1080,
    )
    
    session = BrowserSession(browser_profile=profile)
    await session.start()
    
    await session.navigate_to("https://example.com")
    screenshot = await session.screenshot()
    
    await session.stop()

asyncio.run(main())

# Google (recommended)
export GOOGLE_API_KEY="..."

# OpenAI
export OPENAI_API_KEY="sk-..."

# Anthropic
export ANTHROPIC_API_KEY="sk-ant-..."

# Groq
export GROQ_API_KEY="gsk_..."

# AWS Bedrock
export AWS_ACCESS_KEY_ID="..."
export AWS_SECRET_ACCESS_KEY="..."
export AWS_DEFAULT_REGION="us-west-2"

# Azure OpenAI
export AZURE_OPENAI_API_KEY="..."
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"

from openbrowser import BrowserProfile

profile = BrowserProfile(
    headless=True,
    viewport_width=1280,
    viewport_height=720,
    disable_security=False,
    extra_chromium_args=["--disable-gpu"],
    record_video_dir="./recordings",
    proxy={
        "server": "http://proxy.example.com:8080",
        "username": "user",
        "password": "pass",
    },
)

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

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

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

# 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

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

# 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

openbrowser-ai -c "await navigate('https://example.com')"
openbrowser-ai -c "print(await evaluate('document.title'))"

{
  "mcpServers": {
    "openbrowser": {
      "command": "uvx",
      "args": ["openbrowser-ai", "--mcp"]
    }
  }
}

{
  "mcpServers": {
    "openbrowser": {
      "command": "uvx",
      "args": ["openbrowser-ai", "--mcp"],
      "env": {
        "OPENBROWSER_HEADLESS": "true"
      }
    }
  }
}

uvx openbrowser-ai --mcp

# 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

openbrowser-ai/
├── .claude-plugin/            # Claude Code marketplace config
├── .codex/                    # Codex integration
│   └── INSTALL.md
├── .opencode/                 # OpenCode integration
│   ├── INSTALL.md
│   └── plugins/openbrowser.js
├── plugin/                    # Plugin package (skills + MCP config)
│   ├── .claude-plugin/
│   ├── .mcp.json
│   └── skills/                # 6 browser automation skills
├── src/openbrowser/
│   ├── __init__.py            # Main exports
│   ├── cli.py                 # CLI commands
│   ├── config.py              # Configuration
│   ├── actor/                 # Element interaction
│   ├── agent/                 # LangGraph agent
│   ├── browser/               # CDP browser control
│   ├── code_use/              # Code agent + shared executor
│   ├── daemon/                # Persistent browser daemon (Unix socket)
│   ├── dom/                   # DOM extraction
│   ├── llm/                   # LLM providers
│   ├── mcp/                   # MCP server
│   └── tools/                 # Action registry
├── benchmarks/                # MCP benchmarks and E2E tests
│   ├── playwright_benchmark.py
│   ├── cdp_benchmark.py
│   ├── openbrowser_benchmark.py
│   └── e2e_published_test.py
└── tests/                     # Test suite

# Run unit tests
pytest tests/

# Run with verbose output
pytest tests/ -v

# E2E test the MCP server against the published PyPI package
uv run python benchmarks/e2e_published_test.py

uv run python benchmarks/openbrowser_benchmark.py   # OpenBrowser MCP
uv run python benchmarks/playwright_benchmark.py     # Playwright MCP
uv run python benchmarks/cdp_benchmark.py            # Chrome DevTools MCP

# 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

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

# Build the backend image
docker build -f backend/Dockerfile -t openbrowser-backend .

# Run standalone
docker run -p 8000:8000 -p 6080:6080 \
  --env-file backend/.env \
  -e VNC_ENABLED=true \
  -e AUTH_ENABLED=false \
  --shm-size=2g \
  openbrowser-backend

# Build the frontend image
cd frontend && docker build -t openbrowser-frontend .

# Run standalone
docker run -p 3000:3000 \
  -e NEXT_PUBLIC_API_URL=http://localhost:8000 \
  -e NEXT_PUBLIC_WS_URL=ws://localhost:8000/ws \
  openbrowser-frontend

# Study 1: Autoregressive RL (Qwen3-8B)
# SFT phase -- QLoRA fine-tuning on 992 FormFactory demonstrations (2-4 hours)
python infra/training/finetuning/sft_trainer.py

# Online GRPO phase -- browser-in-the-loop reward (4-8 hours per epoch)
# Requires headless Chromium + FormFactory forms server
python infra/training/shared/formfactory_server.py &   # Start form server
python infra/training/finetuning/online_grpo_trainer.py

# Evaluate SFT and GRPO checkpoints on val/test splits
python infra/training/finetuning/eval_sft.py

# Study 2: Diffusion LM RL (ReFusion 8B, FS-DFM 1.3B)
# SFT phase
python infra/training/flow_matching/fsdfm_sft_trainer.py    # FS-DFM SFT
python infra/training/flow_matching/flow_sft_trainer.py      # ReFusion SFT

# Sequence-level RL (best results)
python infra/training/flow_matching/espo_fsdfm_trainer.py    # ESPO on FS-DFM
python infra/training/flow_matching/espo_refusion_trainer.py # ESPO on ReFusion
python infra/training/flow_matching/mdpo_fsdfm_trainer.py    # MDPO on FS-DFM
python infra/training/flow_matching/mdpo_refusion_trainer.py # MDPO on ReFusion

# Submit jobs to Anyscale cloud
python infra/training/anyscale/submit_job.py --config infra/training/anyscale/online_grpo_job.yaml

# Push trained checkpoints to HuggingFace
python infra/training/anyscale/push_checkpoints_to_hf.py

# Serve trained model locally via vLLM or Ollama
python infra/training/serving/serve_vllm.py
python infra/training/serving/export_gguf.py   # Export to GGUF for Ollama