Give your AI agent
eyes.

import json

with open("tools/tool_definitions.json") as f:
    webscope_tools = json.load(f)["tools"]

response = openai.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Go to example.com"}],
    tools=webscope_tools,
)

from tools.langchain import get_webscope_tools

# Start the server: webscope --serve 3000
tools = get_webscope_tools(base_url="http://localhost:3000")

agent = initialize_agent(tools, llm, agent="zero-shot-react-description")
agent.run("Find the top story on Hacker News")

from tools.crewai import (
    WebScopeBrowseTool, WebScopeClickTool, WebScopeTypeTool
)

researcher = Agent(
    role="Web Researcher",
    tools=[WebScopeBrowseTool(), WebScopeClickTool()],
    llm=llm,
)

# Start the server
$ webscope --serve 3000

# Navigate
$ curl -X POST http://localhost:3000/navigate \
    -H 'Content-Type: application/json' \
    -d '{"url": "https://example.com"}'

# Interact
$ curl -X POST http://localhost:3000/click -d '{"ref": 3}'
$ curl -X POST http://localhost:3000/type -d '{"ref": 7, "text": "hello"}'

const { AgentBrowser } = require('webscope');

const browser = new AgentBrowser({ cols: 120 });
const { view, elements, meta } = await browser.navigate(
  'https://example.com'
);

console.log(view);        // The text grid
console.log(elements);    // { 0: { selector, tag, text, href }, ... }

await browser.click(3);
await browser.type(7, 'hello');
await browser.close();