# Install uv (faster than pip)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install WALT (ideally inside a venv)
uv venv && source .venv/bin/activate
uv pip install sfr-walt
playwright install chromium
# Set up configuration
walt init  # Creates .env file for API keys

# Run agent with tools
walt agent "find and return the URL of the cheapest blue kayak" \
  --tools walt-tools/classifieds/ \
  --start-url http://localhost:9980
# Discover new tools from any website
walt discover --url https://example.com
# Or generate a specific tool (faster!)
walt generate --url https://zillow.com --goal "Search for homes with filters"
# List available tools
walt list walt-tools/shopping/
# Start an MCP server
walt serve walt-tools/classifieds/ --port 8000
# Record a demonstration
walt record https://example.com --name my_tool

# Tool discovery
from walt.tools.discovery import propose, generate
import asyncio
async def discover_tools():
    class Args:
        base_url = "https://example.com"
        output_dir = "my-tools"
        llm = "gpt-5-mini"
        planner_llm = "gpt-5-mini"
        auth_file = None  # Optional: path to Playwright storage_state.json
        max_processes = 16
    args = Args()
    # Phase 1: Discover candidates
    tools = await propose.discover_candidates(args)
    # Phase 2: Generate tools
    await generate.generate_tools(args, tools)
asyncio.run(discover_tools())

# Agent with tools
from walt.browser_use.custom.agent_zoo import VWA_Agent
from walt.browser_use.custom.browser import VWABrowser, BrowserConfig
from walt.browser_use import Controller
from walt.tools.discovery.register import register_tools_from_directory
from langchain_openai import ChatOpenAI
async def run_agent():
    # Setup browser and controller
    browser = VWABrowser(BrowserConfig(headless=False))
    controller = Controller()
    # Load tools
    register_tools_from_directory(
        controller=controller,
        tool_dir="walt-tools/classifieds/",
        llm=ChatOpenAI(model="gpt-5-mini")
    )
    # Create and run agent
    agent = VWA_Agent(
        task="Find the cheapest blue kayak",
        llm=ChatOpenAI(model="gpt-5-mini"),
        browser=browser,
        controller=controller,
        max_actions_per_step=30
    )
    await agent.run()
    await browser.close()
asyncio.run(run_agent())

walt agent "find cheap apartments" --tools walt-tools/classifieds/ --start-url https://www.zillow.com
walt agent "book a flight to NYC" --llm gemini-2.5-flash --max-steps 100 --start-url https://www.google.com/flights
walt agent "search for blue kayaks" --save-gif kayak_search.gif  # Record as GIF

walt discover --url https://example.com
walt discover --url http://localhost:9980 --output walt-tools/mysite
walt discover --url https://example.com --auth-file .auth/state.json
walt discover --url https://example.com --llm gpt-4o --max-processes 8

walt generate --url https://airbnb.com --goal "Search for homes available in a location for provided dates and guest details"
walt generate --url https://zillow.com --goal "View property details" -o walt-tools/zillow/
walt generate --url https://example.com --goal "Book appointment" --auth-file .auth/state.json

walt record https://example.com --name search_products

walt serve walt-tools/shopping/ --port 8000

walt list                           # All tools
walt list walt-tools/classifieds/   # Specific directory
walt list --detailed                # Detailed table view

{
  "name": "search_products",
  "description": "Search for products on the site",
  "inputs": {
    "query": {
      "type": "string",
      "description": "Search query",
      "required": true
    }
  },
  "steps": [
    {
      "type": "navigation",
      "url": "https://example.com"
    },
    {
      "type": "input",
      "cssSelector": "#search-box",
      "text": "{query}"
    },
    {
      "type": "click",
      "cssSelector": "#search-button"
    },
    {
      "type": "extract_page_content",
      "goal": "Extract search results"
    }
  ]
}

git clone https://github.com/salesforceairesearch/walt.git
cd walt
uv venv && source .venv/bin/activate
uv pip install -e ".[dev]"
playwright install chromium

walt/
├── src/walt/
│   ├── browser_use/         # Browser automation
│   ├── tools/               # Tool system (discovery, execution, demonstration)
│   ├── benchmarks/          # WebArena/VisualWebArena evaluation
│   ├── cli.py               # CLI entry point
│   └── config.py            # Configuration system
├── experiment_configs/
│   └── ...                  # Experiment & benchmark configs
├── walt-tools/              # Pre-discovered tools
└── examples/                # Example scripts

# experiment_configs/my_experiment.yaml
name: "My Experiment"
llm:
  agent_model: gpt-5
agent:
  max_steps: 100
output:
  dir: outputs/my-experiment

@article{walt2025,
  title={WALT: Web Agents that Learn Tools},
  author={Viraj Prabhu, Yutong Dai, Matthew Fernandez, Jing Gu, Krithika Ramakrishnan, Yanqi Luo, Silvio Savarese, Caiming Xiong, Junnan Li, Zeyuan Chen, Ran Xu},
  journal={arXiv preprint arXiv:2510.01524},
  year={2025}
}